© 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. 0-CLT-HP
    7. 45528
    Prev
    Next
    INDEX
    Explanations

    sand

    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
     kasarigan
    -0.83
    addCriterion
    -0.76
     ModelExpression
    -0.73
     незавершена
    -0.72
    FieldBuilder
    -0.68
     io
    -0.66
    ########.
    -0.66
    io
    -0.61
    WaitGroup
    -0.61
    parsedMessage
    -0.59
    POSITIVE LOGITS
    ed
    0.62
    DotNetBar
    0.62
    ticing
    0.58
    ing
    0.55
    Pozdrawiam
    0.53
     către
    0.51
     mineures
    0.48
    pushFollow
    0.48
    antaranya
    0.47
    an
    0.47
    Activations Density 1.547%

    No Known Activations