© 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. 20-CLT-HP
    7. 74534
    Prev
    Next
    INDEX
    Explanations

    try

    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
     calendriers
    -0.61
    GEBURTSDATUM
    -0.56
    expandindo
    -0.56
    StoreMessageInfo
    -0.56
    Personensuche
    -0.54
    ('.',
    -0.54
    Sucesor
    -0.52
    ErrUnexpectedEOF
    -0.52
    racene
    -0.52
     nødvendig
    -0.52
    POSITIVE LOGITS
     and
    1.67
    and
    0.82
     và
    0.74
     и
    0.73
    และ
    0.73
     ולה
    0.69
     to
    0.66
    性和
    0.62
     ול
    0.60
     και
    0.60
    Activations Density 0.019%

    No Known Activations