© 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. 71859
    Prev
    Next
    INDEX
    Explanations

    Snippets of sentences

    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
     [*]
    -0.57
     externi
    -0.52
     Squirrel
    -0.51
     Pigeon
    -0.47
    Squirrel
    -0.47
     незавершена
    -0.46
    tvguidetime
    -0.45
    Pro
    -0.45
    pro
    -0.44
    bat
    -0.43
    POSITIVE LOGITS
     gos
    0.66
     geese
    0.65
     hon
    0.65
    TintMode
    0.59
    CardBody
    0.58
    ganu
    0.58
     Penh
    0.57
    ecutive
    0.57
     Bran
    0.56
    Numerology
    0.56
    Activations Density 0.002%

    No Known Activations