© 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. 3100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     '{@
    -0.83
     nahilalakip
    -0.81
    MigrationBuilder
    -0.81
    DockStyle
    -0.77
    ISupport
    -0.76
     contextLoads
    -0.75
    IsContent
    -0.74
     EconPapers
    -0.73
    stood
    -0.72
    ImageContext
    -0.71
    POSITIVE LOGITS
    PLICATION
    0.40
     or
    0.40
     where
    0.39
     silver
    0.38
    or
    0.36
     ||
    0.34
     gene
    0.34
     caval
    0.34
     other
    0.33
     otra
    0.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.