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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43667
    Prev
    Next
    INDEX
    Explanations

    preponderance

    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
    gulation
    -0.66
     Tons
    -0.59
    agine
    -0.57
    ارة
    -0.54
    RunAsync
    -0.54
    ArrowToggle
    -0.54
    thâu
    -0.53
    (")");
    -0.53
    Tons
    -0.52
    Сыртқы
    -0.51
    POSITIVE LOGITS
    AccessorTable
    0.59
     itſelf
    0.58
    verwijspagina
    0.57
     pleaſure
    0.56
     purpoſe
    0.55
     ſtand
    0.54
     greateſt
    0.54
     pleaf
    0.54
     geologic
    0.53
     Eſ
    0.53
    Activations Density 0.153%

    No Known Activations