© 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. 1999
    Prev
    Next
    INDEX
    Explanations

    physiology or pathology

    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
    ftagPool
    -0.73
    
    -0.73
     تضيفلها
    -0.57
    WriteTagHelper
    -0.56
    tvguidetime
    -0.55
    UpdateCommand
    -0.54
    FileDescriptor
    -0.53
     JAXBElement
    -0.52
     TabLayout
    -0.52
    
    -0.50
    POSITIVE LOGITS
    aria
    0.59
    icial
    0.57
    arian
    0.56
    os
    0.55
    ingly
    0.55
    ures
    0.54
    ically
    0.53
    ariat
    0.53
    ably
    0.52
    ag
    0.52
    Activations Density 0.054%

    No Known Activations