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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2382
    Prev
    Next
    INDEX
    Explanations

    geographical areas

    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
     مرئيه
    -0.42
     mať
    -0.42
    etten
    -0.42
    Barn
    -0.40
     cref
    -0.39
     JpaRepository
    -0.39
    StateToProps
    -0.39
    letas
    -0.38
     Moisés
    -0.37
    =[];
    -0.37
    POSITIVE LOGITS
    ftagPool
    0.82
     ویکی‌پدیای
    0.76
    fvar
    0.71
     समीक्षाओं
    0.68
     autorytatywna
    0.68
    Бахар
    0.67
     дописавши
    0.66
     Paglinawan
    0.66
    $_['
    0.62
    nezeu
    0.62
    Activations Density 0.005%

    No Known Activations