© 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. 5-CLT-HP
    7. 603
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    GEBURTSDATUM
    -0.71
    eaways
    -0.65
    principalTable
    -0.57
    always
    -0.54
    Билгалдахарш
    -0.53
    migrationBuilder
    -0.52
     parati
    -0.52
     ſtill
    -0.49
    Belf
    -0.48
     mercies
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.65
    ChildScrollView
    0.59
     ModelRenderer
    0.57
     JADX
    0.56
    исленность
    0.55
    ⓧ
    0.55
     typelib
    0.55
    surate
    0.54
    клопе
    0.53
     Drapeau
    0.52
    Activations Density 0.000%

    No Known Activations