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
    45.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases related to guidelines and regulations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    -
    -0.30
     
    -0.29
     off
    -0.28
    )
    -0.27
    <eos>
    -0.27
     person
    -0.25
     eğ
    -0.25
     leña
    -0.25
    äsident
    -0.25
    \
    -0.25
    POSITIVE LOGITS
    IntoConstraints
    0.93
    rrggbb
    0.79
    <pad>
    0.76
    setVerticalGroup
    0.76
    <unused14>
    0.76
    <unused28>
    0.76
    <unused41>
    0.76
    <unused1>
    0.75
    <unused8>
    0.75
    <unused51>
    0.75
    Act Density 4.578%

    No Known Activations