Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    64
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words that indicate speculation or uncertainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    styleType
    -0.70
    celotti
    -0.63
    нгред
    -0.63
     esternos
    -0.54
    Kariera
    -0.54
     Houſe
    -0.54
    tyimages
    -0.53
     constitutive
    -0.52
    ロウィン
    -0.52
    redient
    -0.52
    POSITIVE LOGITS
     might
    0.65
     if
    0.51
     would
    0.50
     could
    0.50
    might
    0.48
    Might
    0.47
     may
    0.46
     Might
    0.46
    可能會
    0.44
     pourrait
    0.43
    Act Density 0.004%

    No Known Activations