© 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. 4-CLT-HP
    7. 1322
    Prev
    Next
    INDEX
    Explanations

    MacDonald/MCD

    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
     EconPapers
    -0.63
    verifyException
    -0.62
    ArrowToggle
    -0.62
     للاسماء
    -0.61
     itſelf
    -0.59
     незавершена
    -0.59
     HttpServlet
    -0.59
    ValueStyle
    -0.57
     vPvB
    -0.56
    tagext
    -0.56
    POSITIVE LOGITS
     Douglas
    0.52
    Douglas
    0.51
    iland
    0.49
    Silicone
    0.47
     silicone
    0.46
    iastes
    0.46
     dem
    0.45
    mittel
    0.43
    umi
    0.43
    RIOS
    0.43
    Activations Density 0.016%

    No Known Activations