© 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. 0-CLT-HP
    7. 90960
    Prev
    Next
    INDEX
    Explanations

    high quality

    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
     Ausnahme
    -0.56
    attuale
    -0.53
    ppure
    -0.53
    ">'.$
    -0.52
     rápidos
    -0.51
     pulito
    -0.50
     isolato
    -0.50
    __["
    -0.49
     extranjeros
    -0.49
    最快更新
    -0.49
    POSITIVE LOGITS
    expandindo
    0.75
    #
    0.73
    writeFieldEnd
    0.65
     surla
    0.63
    脚注の使い方
    0.62
     CURIAM
    0.61
    devamını
    0.59
     AssemblyCompany
    0.59
    Билгалдахарш
    0.59
     ProtoMessage
    0.58
    Activations Density 0.020%

    No Known Activations