© 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. 98004
    Prev
    Next
    INDEX
    Explanations

    Quotation marks, InteropServices

    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
     typelib
    -0.54
    URLException
    -0.54
    onViewCreated
    -0.53
     تضيفلها
    -0.50
    sizeCache
    -0.48
     crossorigin
    -0.48
    chromedriver
    -0.48
     Pyle
    -0.48
     myeloma
    -0.47
     geleverd
    -0.47
    POSITIVE LOGITS
     IBOutlet
    0.59
     nahilalakip
    0.54
    ltk
    0.52
    HomeAsUpEnabled
    0.50
    Bronnen
    0.50
    Lähteet
    0.49
    kozás
    0.49
    COUVER
    0.48
    Referencer
    0.48
     تعدى
    0.48
    Activations Density 0.003%

    No Known Activations