© 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. 1-CLT-HP
    7. 14387
    Prev
    Next
    INDEX
    Explanations

    peritoneal

    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
    contentLoaded
    -0.74
     CreateTagHelper
    -0.67
    EDEFAULT
    -0.65
    fjspx
    -0.64
     financière
    -0.63
    enderror
    -0.62
     дописавши
    -0.62
     للاسماء
    -0.61
    SaveChangesAsync
    -0.61
    ///</
    -0.61
    POSITIVE LOGITS
    Implications
    0.48
    ształ
    0.46
     housing
    0.45
    BeginContext
    0.42
    AsUp
    0.42
     home
    0.41
     đ
    0.40
    Résumé
    0.40
    del
    0.39
    Nội
    0.39
    Activations Density 0.037%

    No Known Activations