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
    67
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to programming concepts such as classes and interfaces

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     likely
    -0.42
     probably
    -0.40
     obviously
    -0.36
     gemeint
    -0.34
     obvious
    -0.32
     
    -0.31
     Gruß
    -0.31
     nagyobb
    -0.31
    probably
    -0.30
     probablemente
    -0.30
    POSITIVE LOGITS
    ViewInit
    0.78
    StoryboardSegue
    0.73
     interface
    0.66
    ValueStyle
    0.66
     interfaces
    0.64
    transQ
    0.64
     Interfaces
    0.63
    ThroughAttribute
    0.62
    verifyException
    0.62
    IntoConstraints
    0.60
    Act Density 0.010%

    No Known Activations