© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2368
    Prev
    Next
    INDEX
    Explanations

    code formatting

    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
    RegressionTest
    -0.79
    :✨
    -0.78
     otomatig
    -0.65
    webElementXpaths
    -0.64
     الحره
    -0.61
    IUrlHelper
    -0.57
    цезда
    -0.56
    execSQL
    -0.56
     onAnimation
    -0.56
    хьтан
    -0.56
    POSITIVE LOGITS
     Theſe
    0.56
    )";
    0.56
    */;
    0.55
     XNUMX
    0.55
     **/
    0.55
     becauſe
    0.55
    »-
    0.54
     löytyy
    0.54
    {}",
    0.53
     crainte
    0.53
    Activations Density 0.112%

    No Known Activations