© 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. 76398
    Prev
    Next
    INDEX
    Explanations

    website and code snippets

    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
     שוליים
    -0.54
     cue
    -0.53
    Carreira
    -0.52
    */
    -0.50
    ulets
    -0.49
    ריק
    -0.49
    بوابة
    -0.49
    FXMLLoader
    -0.48
    Πηγές
    -0.48
     Wikimédia
    -0.48
    POSITIVE LOGITS
     دیکھیے
    0.71
     Wikimedijinoj
    0.55
    цездатний
    0.51
     typelib
    0.50
    ametro
    0.48
    idends
    0.47
     ErrIntOverflow
    0.47
    +#+
    0.47
    ItemLayout
    0.46
    Démographie
    0.45
    Activations Density 0.003%

    No Known Activations