© 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. 38675
    Prev
    Next
    INDEX
    Explanations

    materials science

    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
     Professional
    -0.74
     expertise
    -0.66
     effectiveness
    -0.54
     tubules
    -0.54
    Professional
    -0.52
    leu
    -0.49
     Professionals
    -0.49
     Geraadpleegd
    -0.48
     P
    -0.48
     linkage
    -0.48
    POSITIVE LOGITS
    ScopeManager
    0.87
    IntoConstraints
    0.69
     NSCoder
    0.66
    theless
    0.64
    parsedMessage
    0.62
    posedge
    0.61
    TextWatcher
    0.61
     Himo
    0.60
    Zeneca
    0.60
    IsContent
    0.57
    Activations Density 0.166%

    No Known Activations