© 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. 43360
    Prev
    Next
    INDEX
    Explanations

    higher

    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
    Higher
    -1.56
    higher
    -1.56
     higher
    -1.51
     Higher
    -1.34
     HIGHER
    -1.23
     highest
    -1.20
    highest
    -1.20
     höheren
    -1.07
    Highest
    -1.04
     Highest
    -1.00
    POSITIVE LOGITS
    קישורים
    0.71
     مشين
    0.68
     שוליים
    0.60
    utnik
    0.57
     earners
    0.56
     références
    0.54
     suspicions
    0.53
    Referências
    0.53
     incomes
    0.53
    DeleteBehavior
    0.53
    Activations Density 0.042%

    No Known Activations