© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78117
    Prev
    Next
    INDEX
    Explanations

    exactness

    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
    Negative Logits
    données
    -0.73
    migrationBuilder
    -0.71
    RegistryLite
    -0.70
     AttributeSet
    -0.69
     ویکی‌پدی
    -0.68
     uska
    -0.68
    rikes
    -0.66
    ibatis
    -0.66
     ostavi
    -0.65
    UnknownFieldSet
    -0.65
    POSITIVE LOGITS
     exactly
    0.54
     Exactly
    0.52
    Exactly
    0.52
     anything
    0.46
     Anything
    0.43
     precisely
    0.41
    exactly
    0.41
    ⓘ
    0.40
     propi
    0.40
     exact
    0.37
    Activations Density 0.000%

    No Known Activations