© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2147
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    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
    ünst
    -0.48
     updated
    -0.46
    reconnect
    -0.45
     triom
    -0.45
    ctu
    -0.44
     updating
    -0.43
     releasing
    -0.43
    práv
    -0.42
     تث
    -0.42
     litter
    -0.42
    POSITIVE LOGITS
     ويكيپيديا
    0.68
     propOrder
    0.67
     ProtoMessage
    0.65
    omock
    0.63
    Abit
    0.57
    focusable
    0.57
    migrationBuilder
    0.57
    IUrlHelper
    0.54
     تضيفلها
    0.54
    setof
    0.53
    Activations Density 0.001%

    No Known Activations