© 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. 39979
    Prev
    Next
    INDEX
    Explanations

    computer architecture/code

    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
    itude
    -1.48
    weis
    -1.15
     Fawcett
    -1.04
    weiss
    -0.72
     Chwiliwch
    -0.60
    weiß
    -0.55
    izr
    -0.54
    habilit
    -0.53
     gambe
    -0.52
    ",""
    -0.52
    POSITIVE LOGITS
    Enllaces
    0.61
     ProtoMessage
    0.59
    +#+#
    0.59
    ⓧ
    0.57
    ScopeManager
    0.57
    帖最后由
    0.57
    PerformLayout
    0.56
    NameInMap
    0.54
    stateParams
    0.54
     thou
    0.52
    Activations Density 0.663%

    No Known Activations