© 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. 1-CLT-HP
    7. 424
    Prev
    Next
    INDEX
    Explanations

    natives

    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
    tvguidetime
    -0.62
     métallique
    -0.61
     Yarm
    -0.59
     Centa
    -0.57
     PAG
    -0.56
     näm
    -0.55
    wapV
    -0.55
     متعلقه
    -0.53
     Übergang
    -0.53
    cassert
    -0.52
    POSITIVE LOGITS
     propOrder
    0.60
    sizeCache
    0.55
    دانشنامهٔ
    0.52
    addCriterion
    0.51
     désolés
    0.51
    evos
    0.49
    CPtr
    0.49
    Билгалдахарш
    0.49
    DeleteBehavior
    0.49
    ModelAdmin
    0.48
    Activations Density 0.026%

    No Known Activations