© 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. 0-CLT-HP
    7. 93388
    Prev
    Next
    INDEX
    Explanations

    beard

    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
     depth
    -0.79
     distant
    -0.55
    juh
    -0.49
     profondità
    -0.49
     solve
    -0.47
     profondeur
    -0.47
     truth
    -0.47
     deberes
    -0.45
     yakın
    -0.44
     Depth
    -0.43
    POSITIVE LOGITS
     الرياضيه
    1.17
     nahilalakip
    1.05
    SharedCtor
    0.95
    QMetaType
    0.92
    MigrationBuilder
    0.91
     հղումներ
    0.91
    migrationBuilder
    0.90
    complexContent
    0.90
    styleType
    0.89
    Personendaten
    0.89
    Activations Density 0.083%

    No Known Activations