INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    52
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuations and numerical values

    New Auto-Interp
    Negative Logits
    DCHECK
    -0.31
    )
    -0.28
    ndale
    -0.28
    obt
    -0.28
    van
    -0.28
     conserv
    -0.27
     batter
    -0.27
     pistes
    -0.27
     Stelle
    -0.26
    Truthy
    -0.26
    POSITIVE LOGITS
    0.78
     kasarigan
    0.76
    LookAnd
    0.71
     noDo
    0.70
     queſta
    0.69
    InstrumentedTest
    0.66
    ंदीखरीदारी
    0.65
    ſelf
    0.64
    fromnode
    0.63
     ſtand
    0.63
    Act Density 3.007%

    No Known Activations