© 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. 13000
    Prev
    Next
    INDEX
    Explanations

    6

    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
    否
    -0.50
    genomen
    -0.50
     Վերցված
    -0.49
    شهاد
    -0.45
    tır
    -0.45
     محفوظة
    -0.45
     匿名
    -0.45
    ülés
    -0.44
    TICK
    -0.44
    СЬ
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.73
    eleste
    0.70
    )_/¯
    0.68
     autorytatywna
    0.68
    TypedDataSet
    0.65
    delwed
    0.64
    ніципа
    0.63
    <>());
    0.61
    Autoritní
    0.61
    hyrchwyd
    0.61
    Activations Density 0.309%

    No Known Activations