© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1294
    Prev
    Next
    INDEX
    Explanations

    see

    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
    enumi
    -0.64
    parseDouble
    -0.59
    ScopeManager
    -0.57
     nourrir
    -0.52
    脚注の使い方
    -0.52
    RectangleBorder
    -0.52
    AccessFile
    -0.51
    rungsseite
    -0.50
    umbersome
    -0.50
    porus
    -0.49
    POSITIVE LOGITS
     NSCoder
    0.65
     if
    0.63
     Abonnez
    0.52
    >{@
    0.52
     <",
    0.51
     Dacă
    0.50
     AspNetCore
    0.50
    if
    0.50
     ơi
    0.49
    Демографія
    0.48
    Activations Density 0.002%

    No Known Activations