© 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. 20-CLT-HP
    7. 72980
    Prev
    Next
    INDEX
    Explanations

    uncommon terms

    np_max-act-logits · 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
    wadi
    -0.58
    SaveChangesAsync
    -0.56
     Pequ
    -0.55
     Pease
    -0.54
    enumii
    -0.53
    enumi
    -0.51
     AppBundle
    -0.51
    <tfoot>
    -0.51
    >{"
    -0.51
     parfa
    -0.51
    POSITIVE LOGITS
    webElement
    0.65
    TagMode
    0.55
     disambiguazione
    0.51
    ☸
    0.50
    homonymie
    0.49
    aarrggbb
    0.48
     lưới
    0.46
    Aure
    0.45
     encontraban
    0.45
     ProtoMessage
    0.44
    Activations Density 0.000%

    No Known Activations