© 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. 94382
    Prev
    Next
    INDEX
    Explanations

    accept

    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
     accept
    -2.58
    accept
    -2.28
     Accept
    -2.14
    Accept
    -2.02
     accepts
    -1.92
     accepting
    -1.90
     Accepting
    -1.81
     aceptar
    -1.52
     ACCEPT
    -1.42
    accepts
    -1.39
    POSITIVE LOGITS
    Geplaatst
    0.87
     مشين
    0.76
     NSCoder
    0.75
    }{*}{
    0.75
    脚注の使い方
    0.72
     متعلقه
    0.71
     the
    0.68
    PostInfinity
    0.66
    GenerationType
    0.66
     cauſe
    0.66
    Activations Density 0.089%

    No Known Activations