© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72046
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     ostavi
    -0.73
    PyExc
    -0.69
    ruptedException
    -0.63
    ulemon
    -0.60
    posedge
    -0.60
    mobileqq
    -0.59
    ########.
    -0.58
     autorytatywna
    -0.58
     مشارکت‌کنندگان
    -0.55
    sizeCache
    -0.55
    POSITIVE LOGITS
     research
    0.56
    Research
    0.52
     Research
    0.50
    UnknownFieldSet
    0.48
    ագ
    0.46
    աց
    0.45
    research
    0.44
    บ
    0.43
     RESEARCH
    0.43
     acresc
    0.43
    Activations Density 0.001%

    No Known Activations