© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91937
    Prev
    Next
    INDEX
    Explanations

    granted

    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
    Према
    -0.60
     regularization
    -0.58
    Przypisy
    -0.58
    bootstrapcdn
    -0.57
    titleMargin
    -0.52
     regularity
    -0.50
     Dagger
    -0.50
    MIDDLEWARE
    -0.50
    TableAdapter
    -0.48
    UnitTesting
    -0.48
    POSITIVE LOGITS
     اكتوبر
    0.59
    ByteBuf
    0.57
     >=",
    0.55
    ioms
    0.54
    ?>
    0.52
    subpackage
    0.52
    èlement
    0.50
    URLException
    0.50
    towej
    0.50
    évaluateur
    0.48
    Activations Density 0.032%

    No Known Activations