INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
73
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
terms and references related to superheroes and heroic characters
New Auto-Interp
Negative Logits
LabelTagHelper
-0.62
/**
-0.60
出版年
-0.59
AssemblyCulture
-0.56
Hochspringen
-0.56
/*++
-0.55
Paglinawan
-0.54
⤒
-0.54
andExpect
-0.53
ERVIEW
-0.52
POSITIVE LOGITS
hero
0.47
heroes
0.47
superheroes
0.42
characters
0.41
superhero
0.40
hero
0.37
heroes
0.36
héro
0.34
role
0.34
🦸
0.34
Activations Density 0.000%