INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
55.75
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
references to strings, numbers, and temperatures in programming contexts
New Auto-Interp
Negative Logits
ویکیپدی
-0.68
مرئيه
-0.59
➟
-0.57
]]:
-0.57
Italijanski
-0.53
contentLoaded
-0.52
GEBURTS
-0.52
"}},
-0.50
RTDA
-0.49
Hochspringen
-0.48
POSITIVE LOGITS
Története
0.45
skolan
0.44
0.42
gedrag
0.42
ülés
0.41
chaud
0.39
neceff
0.38
durs
0.38
libft
0.38
juſ
0.37
Activations Density 0.002%