© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11910
    Prev
    Next
    INDEX
    Explanations

    shoes

    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
     shoe
    -2.44
     shoes
    -2.44
     Shoe
    -2.19
     Shoes
    -2.17
    shoe
    -1.99
    shoes
    -1.97
    Shoe
    -1.91
     SHOES
    -1.88
    Shoes
    -1.88
     footwear
    -1.79
    POSITIVE LOGITS
    ep
    0.49
    agod
    0.46
    parade
    0.46
    ALLE
    0.45
    Wol
    0.44
    charter
    0.44
    making
    0.44
    ex
    0.44
    таж
    0.43
     وتسجيلات
    0.43
    Activations Density 0.008%

    No Known Activations