© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4601
    Prev
    Next
    INDEX
    Explanations

    Synd

    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
     lenker
    -0.56
    priate
    -0.47
     dabei
    -0.46
    eek
    -0.46
    neapolis
    -0.46
    atán
    -0.45
    '],
    
    -0.44
     ra
    -0.43
     ass
    -0.42
     hor
    -0.42
    POSITIVE LOGITS
    ContentAsync
    0.75
    enumi
    0.72
     المعيارى
    0.71
     EconPapers
    0.70
    DoubleQuotes
    0.67
     متعلقه
    0.65
    abestanden
    0.63
    multirow
    0.60
     ujednoznacz
    0.60
    RenderAtEndOf
    0.59
    Activations Density 0.027%

    No Known Activations