© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5475
    Prev
    Next
    INDEX
    Explanations

    medical reconstruction/regeneration

    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
    Portale
    -0.68
     protoimpl
    -0.59
     pageContext
    -0.56
    ValueGeneration
    -0.55
    >−
    -0.54
     AssemblyCulture
    -0.54
    
    -0.54
    DeleteBehavior
    -0.54
    expandindo
    -0.54
    بوابة
    -0.54
    POSITIVE LOGITS
     medicine
    0.54
     Anspruch
    0.54
     Tread
    0.48
    Surge
    0.48
    出版年
    0.47
     générales
    0.47
     ClassNotFound
    0.46
     táctil
    0.46
     vettore
    0.45
     Medicine
    0.45
    Activations Density 0.003%

    No Known Activations