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
    78.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms associated with structured frameworks or guidelines

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HttpFoundation
    -0.51
    Smarty
    -0.46
    SequentialGroup
    -0.44
    Personendaten
    -0.43
    lito
    -0.43
    zheimer
    -0.42
     Мексичка
    -0.42
    WriteTagHelper
    -0.42
    äsident
    -0.41
    gemeen
    -0.40
    POSITIVE LOGITS
     criteria
    0.49
     standards
    0.47
     specifications
    0.46
    FormState
    0.45
     guidelines
    0.45
    ValueStyle
    0.43
     exigences
    0.42
    awtextra
    0.42
    Calidad
    0.42
     Criteria
    0.42
    Act Density 0.001%

    No Known Activations