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
    48.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    function definitions in programming code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    }{*}{
    -0.46
    lewati
    -0.38
     cintura
    -0.38
    Diweddarwch
    -0.38
    -------------</
    -0.37
    Personendaten
    -0.37
    ViewStyle
    -0.37
     někdo
    -0.36
     cucharadita
    -0.36
    Carreira
    -0.36
    POSITIVE LOGITS
    MessageTagHelper
    0.57
     propOrder
    0.56
    DebuggerStep
    0.55
    WithIOException
    0.54
    cupa
    0.54
    XmlAccessorType
    0.50
    setVerticalGroup
    0.50
    InstrumentedTest
    0.50
     Clau
    0.48
    +:+
    0.47
    Act Density 0.028%

    No Known Activations