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

    structured data and explicit indications of agreement or confirmation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    intahan
    -0.38
    tagext
    -0.35
     nawr
    -0.35
    letzt
    -0.35
     générales
    -0.34
    isième
    -0.34
    Spoiler
    -0.33
    umenical
    -0.33
    zarchiwizowane
    -0.32
     cref
    -0.32
    POSITIVE LOGITS
    ########.
    0.61
     Taktlose
    0.59
     purpoſe
    0.54
     Administrativna
    0.53
    ContentAlignment
    0.48
     noDo
    0.48
    ViewInit
    0.48
     betweenstory
    0.47
    NOPQRST
    0.46
    AutoScale
    0.46
    Act Density 2.235%

    No Known Activations