© 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. 39796
    Prev
    Next
    INDEX
    Explanations

    editing

    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
     editors
    -0.68
    editors
    -0.55
    Editors
    -0.52
     EDITORS
    -0.49
    ver
    -0.48
     ideia
    -0.47
     Editors
    -0.47
    RequestParam
    -0.44
    ta
    -0.43
    ıştı
    -0.42
    POSITIVE LOGITS
    LabelTagHelper
    0.75
     فريبيس
    0.68
    henswürdigkeiten
    0.68
    ftagPool
    0.66
     testSet
    0.63
     kasarigan
    0.60
    COUVER
    0.60
    ędzynarod
    0.59
    skjaer
    0.59
    Materiał
    0.59
    Activations Density 1.392%

    No Known Activations