© 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. 1-CLT-HP
    7. 12301
    Prev
    Next
    INDEX
    Explanations

    format

    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
    Format
    -0.81
     Format
    -0.79
     format
    -0.77
    format
    -0.72
     Formato
    -0.52
     formato
    -0.52
     формат
    -0.52
     FORMAT
    -0.49
    格式
    -0.49
    FORMAT
    -0.48
    POSITIVE LOGITS
     AssemblyProduct
    0.86
    Przypisy
    0.75
    ViewFeatures
    0.74
    migrationBuilder
    0.71
     EconPapers
    0.71
    ISupport
    0.71
    AddTagHelper
    0.70
     Baillargeon
    0.70
    Referințe
    0.69
    WriteBarrier
    0.66
    Activations Density 0.045%

    No Known Activations