© 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. 5-CLT-HP
    7. 96523
    Prev
    Next
    INDEX
    Explanations

    than

    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
     själ
    -0.57
     inalámb
    -0.52
    $'
    -0.50
    NewUrlParser
    -0.50
    SPATH
    -0.48
    quoise
    -0.48
     محفوظة
    -0.48
     nahilalakip
    -0.48
     مؤرشف
    -0.47
     considérons
    -0.46
    POSITIVE LOGITS
     AssemblyProduct
    0.63
    RunAsync
    0.62
     anything
    0.61
    Anything
    0.59
    oredCriteria
    0.58
     Anything
    0.57
     समीक्षक
    0.56
    Décès
    0.56
    WithIOException
    0.55
    UnsafeEnabled
    0.54
    Activations Density 0.003%

    No Known Activations