© 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. 95480
    Prev
    Next
    INDEX
    Explanations

    past tense

    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
    ged
    -0.73
    ger
    -0.73
    burn
    -0.73
    mented
    -0.68
    bert
    -0.59
    tile
    -0.55
    gang
    -0.54
    wal
    -0.54
    war
    -0.53
    ment
    -0.52
    POSITIVE LOGITS
     Normdatei
    0.95
    RenderAtEndOf
    0.88
     Efq
    0.85
    ++
    0.82
     للاسماء
    0.82
    =$?
    0.81
     незавершена
    0.78
     Jefus
    0.77
     DBNull
    0.77
    >");
    0.76
    Activations Density 0.314%

    No Known Activations