© 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. 40476
    Prev
    Next
    INDEX
    Explanations

    locations, disasters, infrastructure

    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
    Plumbing
    -0.66
     Pest
    -0.64
     disparu
    -0.63
    omock
    -0.63
     FURNITURE
    -0.61
     Plumbing
    -0.60
    出版年
    -0.60
     <=",
    -0.59
     réaliste
    -0.59
    ysan
    -0.59
    POSITIVE LOGITS
    s
    0.76
    sted
    0.51
    StartCoroutine
    0.46
    t
    0.46
    sage
    0.45
    getline
    0.44
    zta
    0.44
     IndexPath
    0.44
     onCancelled
    0.42
    rily
    0.42
    Activations Density 0.227%

    No Known Activations