© 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. 20-CLT-HP
    7. 72470
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
    makeText
    -0.69
    HandlerContext
    -0.66
    aarrggbb
    -0.66
     насељу
    -0.65
    localctx
    -0.65
    PageRoute
    -0.63
    Personensuche
    -0.62
     Audiodateien
    -0.60
     <<<<<<<<<<<<<<
    -0.60
    atchewan
    -0.60
    POSITIVE LOGITS
    DeleteCommand
    0.46
     noires
    0.45
    epy
    0.43
     Fourth
    0.43
     enfans
    0.43
     condamné
    0.42
    ^[
    0.41
     préfé
    0.41
     kelapa
    0.41
    __;
    0.40
    Activations Density 0.006%

    No Known Activations