In this article we approach neural networks as computational templates that travel across various sciences. Traditionally, it has been thought that models are primarily models of some target systems: they are assumed to represent partially or completely their target systems. We argue, instead, that many computational models cannot easily be conceived of in representational terms. Rather, they can be seen as models for various epistemic endeavors. Apart from dealing with the question of representation, we discuss also what implications the genuinely cross-disciplinary computational templates such as neural networks have for the organization of science. We use Self-organizing maps as an example through which we study the aforementioned questions.