INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
63.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
terms associated with leakage, flow, and transportation
New Auto-Interp
Negative Logits
Vira
-0.50
Ανακτήθηκε
-0.49
celotti
-0.49
Smarty
-0.48
Dominant
-0.47
zenberg
-0.47
Personendaten
-0.47
mila
-0.47
tyimages
-0.46
electrically
-0.45
POSITIVE LOGITS
ValueStyle
0.49
leakage
0.48
fromnode
0.47
leak
0.46
leak
0.46
########.
0.44
seepage
0.42
Guinée
0.42
Leak
0.41
leaks
0.41
Activations Density 0.001%