© 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. 20-CLT-HP
    7. 76439
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · 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
     للاسماء
    -0.57
    XmlAccessorType
    -0.54
    NORE
    -0.50
    cookieParser
    -0.50
    AlterField
    -0.50
    RepeatedField
    -0.49
    Gears
    -0.49
    IUrlHelper
    -0.49
     ioutil
    -0.48
    ghter
    -0.48
    POSITIVE LOGITS
    сылкі
    0.54
    Música
    0.50
    AntiForgeryToken
    0.50
    usercontent
    0.49
    例句
    0.48
    FTFY
    0.46
    centration
    0.46
     invitation
    0.45
    lasse
    0.45
     ویکی‌آمباردا
    0.44
    Activations Density 0.001%

    No Known Activations