© 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. 4-CLT-HP
    7. 914
    Prev
    Next
    INDEX
    Explanations

    certificates and mathematical curves

    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
    IntoConstraints
    -0.72
    berti
    -0.62
    IndentedString
    -0.61
    ViewFeatures
    -0.56
    hiti
    -0.55
     صوتيه
    -0.55
    이버
    -0.54
    stateProvider
    -0.51
    writeFieldEnd
    -0.51
    iver
    -0.50
    POSITIVE LOGITS
    OOC
    0.60
    OC
    0.59
    ooc
    0.49
    woocommerce
    0.48
     OCS
    0.47
     OC
    0.47
     Münch
    0.46
    ccl
    0.46
    devtool
    0.46
    addOn
    0.46
    Activations Density 0.002%

    No Known Activations