INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
58
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
key phrases related to research findings and the need for further investigation
New Auto-Interp
Negative Logits
:✨
-0.64
Paglinawan
-0.59
Personendaten
-0.58
ofrecerte
-0.50
estacks
-0.49
supersonic
-0.48
Blitz
-0.47
ِّف
-0.47
nitrous
-0.46
IFTT
-0.46
POSITIVE LOGITS
ควร
0.45
insight
0.41
suggestions
0.40
débats
0.40
insights
0.39
exploración
0.39
โท
0.38
sugger
0.38
不宜
0.38
suggested
0.38
Activations Density 0.021%