INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
81.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
words related to uncovering or revealing information
New Auto-Interp
Negative Logits
AddTagHelper
-0.67
tableFuture
-0.59
Référence
-0.58
estacks
-0.58
rodríguez
-0.56
tanleria
-0.56
فريبيس
-0.53
djangoproject
-0.53
Smarty
-0.52
нгред
-0.52
POSITIVE LOGITS
revealing
0.71
dévo
0.69
reveal
0.65
reveals
0.65
revealed
0.63
reveal
0.63
uncovering
0.60
révèle
0.60
revelar
0.60
révé
0.57
Activations Density 0.000%