© 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. 74516
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     مشين
    -0.49
    фов
    -0.39
    ידי
    -0.38
    AVER
    -0.38
     safe
    -0.38
    deld
    -0.38
     bun
    -0.37
     صوتيه
    -0.37
    umel
    -0.37
     rid
    -0.36
    POSITIVE LOGITS
    twimg
    0.77
     Anſ
    0.71
    ⓧ
    0.66
     Económica
    0.65
    migrationBuilder
    0.64
    asgi
    0.63
     виправивши
    0.63
    Locality
    0.60
     disambiguazione
    0.59
    zaamheid
    0.59
    Activations Density 0.000%

    No Known Activations