© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14466
    Prev
    Next
    INDEX
    Explanations

    scratch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scratch
    -0.59
    Scratch
    -0.58
    scratch
    -0.54
     Scratch
    -0.52
    copyWith
    -0.47
     scratching
    -0.40
     SIMBAD
    -0.39
    롭
    -0.39
     random
    -0.39
    InitVars
    -0.39
    POSITIVE LOGITS
     مشين
    0.69
     виправивши
    0.68
     Familienname
    0.63
    titleMargin
    0.61
    ContentLoaded
    0.60
    MessageTagHelper
    0.59
     PropTypes
    0.58
    AlterField
    0.57
    InView
    0.57
     gages
    0.57
    Activations Density 0.104%

    No Known Activations