© 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. 5-CLT-HP
    7. 3973
    Prev
    Next
    INDEX
    Explanations

    size

    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
     démocr
    -0.62
    fromnode
    -0.59
    ContentLoaded
    -0.57
     idéia
    -0.55
     chré
    -0.54
     enfans
    -0.54
     féminine
    -0.54
     singola
    -0.53
     espirituales
    -0.53
     duquel
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
     (
    0.60
    IBarButtonItem
    0.59
     AspNetCore
    0.59
     new
    0.57
     Scale
    0.56
    thodox
    0.54
     newOwner
    0.52
    MigrationBuilder
    0.52
    TintMode
    0.52
    Activations Density 0.007%

    No Known Activations