© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1039
    Prev
    Next
    INDEX
    Explanations

    '

    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
    ...</
    -0.47
     connexes
    -0.42
    CHRON
    -0.41
     ему
    -0.39
     지
    -0.39
     ho
    -0.39
     годах
    -0.38
    atação
    -0.38
    付け
    -0.38
    ArgsConstructor
    -0.38
    POSITIVE LOGITS
     purpoſe
    0.90
    MigrationBuilder
    0.83
    mobileqq
    0.82
     EconPapers
    0.81
     ویکی‌پدی
    0.80
    GEBURTSDATUM
    0.79
     AssemblyProduct
    0.74
     Monfieur
    0.74
     initComponents
    0.73
    IGraphics
    0.72
    Activations Density 0.000%

    No Known Activations