© 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. 11361
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
     оригіналу
    -0.44
    ediat
    -0.43
    asun
    -0.41
     становника
    -0.40
    Sudoku
    -0.39
    adi
    -0.39
    ::_('
    -0.37
    emate
    -0.37
    ao
    -0.36
    رشف
    -0.36
    POSITIVE LOGITS
     Houſe
    0.93
     Efq
    0.85
     Theſe
    0.82
     Diſ
    0.80
     Anſ
    0.78
     uſed
    0.77
     fubject
    0.77
     Inſ
    0.77
     occaf
    0.75
     neceffary
    0.74
    Activations Density 0.015%

    No Known Activations