© 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. 90673
    Prev
    Next
    INDEX
    Explanations

    similar

    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
     stands
    -0.71
     measures
    -0.62
     lies
    -0.61
     mounts
    -0.61
     calls
    -0.59
     holds
    -0.59
     cycles
    -0.57
     rests
    -0.57
     represents
    -0.57
     flows
    -0.57
    POSITIVE LOGITS
     vœux
    0.80
     prisonniers
    0.77
     ouvriers
    0.74
     FetchType
    0.72
     leçons
    0.72
     travailleurs
    0.71
     vérit
    0.70
     épaules
    0.70
    __":
    0.68
     >=",
    0.66
    Activations Density 0.255%

    No Known Activations