© 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. 12958
    Prev
    Next
    INDEX
    Explanations

    ating

    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
     SIMBAD
    -0.65
    ologist
    -0.53
     Dish
    -0.48
    er
    -0.48
     behar
    -0.47
    ster
    -0.47
    ระ
    -0.47
     PyTuple
    -0.47
     McMahon
    -0.46
    {},
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.90
     مرئيه
    0.87
    zzleHttp
    0.84
    Viitteet
    0.78
     дописавши
    0.77
    SPATH
    0.75
    abestanden
    0.74
    MigrationBuilder
    0.73
     MainAxisSize
    0.73
     nakalista
    0.71
    Activations Density 0.018%

    No Known Activations