© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91973
    Prev
    Next
    INDEX
    Explanations

    delays, networking, repetition

    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
    rep
    -0.94
    REP
    -0.61
    adi
    -0.57
     postponed
    -0.55
     postpone
    -0.54
    (
    -0.54
     []:
    -0.53
     округа
    -0.53
    as
    -0.53
     meets
    -0.52
    POSITIVE LOGITS
    MigrationBuilder
    0.76
    rostis
    0.65
     propOrder
    0.64
    %</
    0.60
    الحياه
    0.60
    ammen
    0.57
    erees
    0.55
    cotch
    0.54
     Efq
    0.54
     ويكيپيديا
    0.53
    Activations Density 1.625%

    No Known Activations