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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3021
    Prev
    Next
    INDEX
    Explanations

    order

    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
    روابط
    -0.46
    expandindo
    -0.45
    rotz
    -0.45
    öv
    -0.44
    databind
    -0.42
    IComponent
    -0.42
    removeAll
    -0.40
     ExecuteAsync
    -0.40
    stdc
    -0.40
    DataAnnotations
    -0.40
    POSITIVE LOGITS
     of
    0.89
    ScopeManager
    0.78
     EconPapers
    0.72
    ядок
    0.66
     they
    0.60
    TagMode
    0.58
     spørs
    0.57
    lapsingToolbar
    0.57
    kező
    0.55
    LayoutPanel
    0.54
    Activations Density 0.003%

    No Known Activations