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
    38.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific phrases and terminology related to technical or engineering contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     beliau
    -0.32
     peringatan
    -0.32
     
    -0.29
     lisäksi
    -0.29
     wypo
    -0.28
     férias
    -0.28
     legais
    -0.28
     far
    -0.28
     væ
    -0.27
     katanya
    -0.27
    POSITIVE LOGITS
    <unused1>
    0.73
    <unused28>
    0.73
    <unused3>
    0.73
    <unused14>
    0.73
    <unused41>
    0.73
    <unused47>
    0.73
    <unused51>
    0.73
    <unused74>
    0.73
    <unused79>
    0.73
    [@BOS@]
    0.73
    Act Density 6.904%

    No Known Activations