© 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. 5-CLT-HP
    7. 5762
    Prev
    Next
    INDEX
    Explanations

    install

    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
    timation
    -0.50
     élé
    -0.43
     مُعرِّف
    -0.40
    eseen
    -0.39
    CultureInfo
    -0.37
    Ndr
    -0.36
     Italijanski
    -0.35
    MathML
    -0.34
     enige
    -0.34
     modalités
    -0.34
    POSITIVE LOGITS
    CloseOperation
    0.96
    ✨:
    0.83
    цездатний
    0.78
     مشين
    0.72
     nahilalakip
    0.71
    )))));
    0.69
    +#+#
    0.69
     autorytatywna
    0.68
     OFDb
    0.68
    VersionUID
    0.66
    Activations Density 0.038%

    No Known Activations