© 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. 77479
    Prev
    Next
    INDEX
    Explanations

    varied source texts

    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
     CURIAM
    -0.88
    KommentareTeilen
    -0.73
     kasarigan
    -0.69
    帖最后由
    -0.67
    __(/*!
    -0.66
    ########.
    -0.64
    ++]=
    -0.64
    Tikang
    -0.63
     aze
    -0.63
    TagMode
    -0.62
    POSITIVE LOGITS
     the
    0.50
    kháu
    0.48
     varandra
    0.45
    sizeCache
    0.39
    null
    0.38
    esa
    0.37
     cada
    0.37
    GEBURTSDATUM
    0.37
     Every
    0.36
    Each
    0.36
    Activations Density 0.001%

    No Known Activations