© 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. 97321
    Prev
    Next
    INDEX
    Explanations

    scientific and medical language

    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
    <bos>
    -0.63
     للاسماء
    -0.59
    MLLoader
    -0.50
    ChildScrollView
    -0.47
    verwijspagina
    -0.47
    etheless
    -0.46
    etcode
    -0.44
    vendo
    -0.44
    UrlResolution
    -0.44
    ℗
    -0.43
    POSITIVE LOGITS
    
    0.64
     Nobles
    0.61
     خارجية
    0.60
     فريبيس
    0.58
     flow
    0.57
     permeability
    0.57
    Tabbed
    0.56
     plafon
    0.56
     Affiliations
    0.54
    onOptions
    0.54
    Activations Density 0.294%

    No Known Activations