© 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. 1-CLT-HP
    7. 13542
    Prev
    Next
    INDEX
    Explanations

    Tucson

    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
     Hilary
    -0.59
    Hilary
    -0.50
    thenia
    -0.48
     ISNI
    -0.48
    utilisons
    -0.47
     resourceCulture
    -0.47
     Himo
    -0.47
    Clue
    -0.46
    ($__
    -0.44
     getItemId
    -0.44
    POSITIVE LOGITS
    mann
    0.55
    sus
    0.53
    namental
    0.51
    stalt
    0.51
    GeoNames
    0.51
    manan
    0.50
    ms
    0.50
     laba
    0.49
    zydent
    0.49
     ming
    0.49
    Activations Density 0.054%

    No Known Activations