© 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. 40075
    Prev
    Next
    INDEX
    Explanations

    established, located

    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
    payers
    -1.02
    standers
    -0.91
    Founded
    -0.85
    taxia
    -0.81
    帖最后由
    -0.81
     Founded
    -0.80
    Established
    -0.79
    phans
    -0.76
     GeoNames
    -0.76
    UserScript
    -0.76
    POSITIVE LOGITS
     by
    0.66
     in
    0.64
     on
    0.61
     the
    0.59
     an
    0.55
     as
    0.52
     se
    0.50
     at
    0.49
     a
    0.48
     under
    0.48
    Activations Density 0.276%

    No Known Activations