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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13089
    Prev
    Next
    INDEX
    Explanations

    strophy

    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
    acco
    -0.89
    stad
    -0.88
    strophy
    -0.65
    льд
    -0.42
    omin
    -0.41
    iche
    -0.40
     pase
    -0.40
    stads
    -0.40
    ime
    -0.40
    lainen
    -0.39
    POSITIVE LOGITS
    ngdoc
    0.87
     autorytatywna
    0.83
    aarrggbb
    0.81
     disambiguazione
    0.81
    UnsafeEnabled
    0.77
     متعلقه
    0.71
     Signalez
    0.69
    mobileqq
    0.67
    يميديا
    0.65
    jooq
    0.65
    Activations Density 0.017%

    No Known Activations