© 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. 0-CLT-HP
    7. 42735
    Prev
    Next
    INDEX
    Explanations

    Conclusion

    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
    hampton
    -1.11
    Conclusion
    -0.93
     Wikimédia
    -0.73
    CONCLUSION
    -0.69
     ویکی‌پدی
    -0.68
     EconPapers
    -0.65
     canadensis
    -0.65
    GrantedAuthority
    -0.63
     overseen
    -0.63
    interopRequire
    -0.62
    POSITIVE LOGITS
    uncur
    0.52
     Service
    0.47
     BoxDecoration
    0.47
    TypeService
    0.45
    Service
    0.45
    cadilly
    0.44
     Division
    0.43
     Form
    0.43
     main
    0.42
    asures
    0.42
    Activations Density 0.083%

    No Known Activations