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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10752
    Prev
    Next
    INDEX
    Explanations

    ability

    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
    AsUp
    -0.85
     AspNetCore
    -0.71
     المعيارى
    -0.70
    memoized
    -0.69
     HasFactory
    -0.68
    ImageContext
    -0.67
     unknownFields
    -0.66
    PyExc
    -0.66
    enderror
    -0.63
    IVEREF
    -0.63
    POSITIVE LOGITS
     Index
    0.52
    index
    0.50
    hen
    0.50
     comentário
    0.48
    CrossRef
    0.47
     cellpadding
    0.47
    SourceChecksum
    0.47
    ⎩
    0.46
     index
    0.46
    achal
    0.43
    Activations Density 0.116%

    No Known Activations