© 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. 20-CLT-HP
    7. 74763
    Prev
    Next
    INDEX
    Explanations

    Computer code and file paths

    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
    ValueStyle
    -0.94
     disambiguazione
    -0.86
    Vidite
    -0.86
    EndGlobalSection
    -0.85
    ThroughAttribute
    -0.85
    MigrationBuilder
    -0.84
    aarrggbb
    -0.81
     comuniques
    -0.80
    исленность
    -0.79
     propOrder
    -0.79
    POSITIVE LOGITS
     tri
    0.41
    coa
    0.41
     the
    0.39
     Mor
    0.36
     Y
    0.35
     R
    0.35
     Tr
    0.35
     Tri
    0.34
     Mon
    0.34
     its
    0.34
    Activations Density 0.004%

    No Known Activations