© 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. 0-CLT-HP
    7. 95574
    Prev
    Next
    INDEX
    Explanations

    C

    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
    Negative Logits
    C
    -1.02
     C
    -0.91
    fromnode
    -0.59
     close
    -0.54
     actual
    -0.52
    CURY
    -0.50
    erto
    -0.50
     fast
    -0.49
     Crosse
    -0.48
    Cantidad
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.88
    HtmlAttribute
    0.83
     myſelf
    0.81
     تانيه
    0.78
     Normdatei
    0.76
     Reſ
    0.75
     незавершена
    0.74
    DoubleQuotes
    0.74
     Anſ
    0.73
     Diſ
    0.72
    Activations Density 0.640%

    No Known Activations