© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77874
    Prev
    Next
    INDEX
    Explanations

    Summaries and analyses

    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
    Население
    -0.49
     basan
    -0.46
    ADVERTISEMENT
    -0.45
    onFocus
    -0.42
    參考文獻
    -0.41
     må
    -0.41
    ázaro
    -0.40
    Improvement
    -0.39
     mesto
    -0.39
    Références
    -0.38
    POSITIVE LOGITS
    Autoritní
    0.82
    SourceChecksum
    0.79
     незавершена
    0.79
    ImageContext
    0.77
     للاسماء
    0.76
     AssemblyTitle
    0.76
    __*/
    0.75
     وتسجيلات
    0.74
     الرياضيه
    0.72
    DeleteBehavior
    0.72
    Activations Density 0.000%

    No Known Activations