© 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. 93521
    Prev
    Next
    INDEX
    Explanations

    historical data/numbers

    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
    !*\
    -0.57
     հղումներ
    -0.52
    BufferException
    -0.48
    Jeografia
    -0.46
    mphony
    -0.46
     ex
    -0.45
    lapsingToolbar
    -0.43
     thous
    -0.43
    يكب
    -0.42
    resu
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.65
    Autoritní
    0.63
     StatelessWidget
    0.63
    tagHelperRunner
    0.62
    Hochspringen
    0.56
     affitto
    0.54
     الحره
    0.53
    tagext
    0.53
    GEBURTSDATUM
    0.53
     CONTENTS
    0.52
    Activations Density 0.002%

    No Known Activations