© 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. 4-CLT-HP
    7. 1817
    Prev
    Next
    INDEX
    Explanations

    with

    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
    rungsseite
    -0.77
     propOrder
    -0.58
     transfieras
    -0.54
     przeci
    -0.53
     officers
    -0.51
     alent
    -0.51
    JsonInclude
    -0.50
    asic
    -0.49
     Verg
    -0.48
     typelib
    -0.48
    POSITIVE LOGITS
    הערות
    0.67
     a
    0.67
    migrationBuilder
    0.56
     ویکی‌پدی
    0.54
    AutoSize
    0.53
     crossorigin
    0.51
    Synonymes
    0.46
    WSER
    0.46
    dasarkan
    0.46
    zur
    0.46
    Activations Density 0.002%

    No Known Activations