© 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. 95182
    Prev
    Next
    INDEX
    Explanations

    UnityEngine

    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
     grà
    -0.54
    LookAnd
    -0.53
     begyn
    -0.53
    WireFormat
    -0.52
    帖最后由
    -0.50
     finally
    -0.48
     \%
    -0.47
     disambiguazione
    -0.46
     begun
    -0.46
    ="<?
    -0.46
    POSITIVE LOGITS
     myſelf
    0.94
     Jefus
    0.91
     Eſ
    0.90
     ſeveral
    0.90
     Monfieur
    0.90
     againſt
    0.87
     Theſe
    0.87
     Chriſt
    0.85
     itſelf
    0.84
     himſelf
    0.83
    Activations Density 0.303%

    No Known Activations