© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92477
    Prev
    Next
    INDEX
    Explanations

    medical scans and organs

    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
    IUrlHelper
    -1.18
    ValueStyle
    -1.01
    +#+#
    -0.98
     وتسجيلات
    -0.98
     smelled
    -0.96
     Infórmanos
    -0.95
     nahilalakip
    -0.94
    extAlignment
    -0.94
    évaluateur
    -0.92
    存于互联网档案馆
    -0.90
    POSITIVE LOGITS
     of
    0.71
    ing
    0.66
    ,
    0.64
    .
    0.57
    ner
    0.54
    in
    0.54
    king
    0.53
    se
    0.52
    rix
    0.52
    ster
    0.50
    Activations Density 1.790%

    No Known Activations