© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95457
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
     betweenstory
    -1.02
     snippetHide
    -0.92
    webElementXpaths
    -0.79
    
    -0.77
     myſelf
    -0.74
     EconPapers
    -0.73
    GEBURTSDATUM
    -0.71
     initComponents
    -0.71
    setVerticalGroup
    -0.69
    ValueStyle
    -0.69
    POSITIVE LOGITS
     clinical
    0.54
     c
    0.52
     zo
    0.52
     infected
    0.52
     with
    0.50
    </
    0.50
    セ
    0.49
    </i>
    0.49
     clinically
    0.49
    elan
    0.48
    Activations Density 0.184%

    No Known Activations