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
    35.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to candidates and elections in legal contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    assertRaises
    -0.30
     condena
    -0.30
     
    -0.30
     be
    -0.30
     AssemblyVersion
    -0.29
    ]
    -0.29
    酒屋
    -0.28
     really
    -0.28
     dan
    -0.27
     running
    -0.27
    POSITIVE LOGITS
     betweenstory
    0.82
    transQ
    0.76
     propOrder
    0.67
    rrggbb
    0.66
    <unused14>
    0.63
    <unused3>
    0.63
    <unused8>
    0.63
    <unused21>
    0.63
    <unused28>
    0.63
    <unused41>
    0.63
    Act Density 8.815%

    No Known Activations