© 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. 45874
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Penh
    -0.49
     nationality
    -0.47
     buffalo
    -0.47
     Venise
    -0.46
     vineyard
    -0.46
    chitis
    -0.46
     ویکی‌پدیای
    -0.45
     pleaſure
    -0.45
     вікі
    -0.45
     frankfurt
    -0.45
    POSITIVE LOGITS
    InputBorder
    0.55
     Mark
    0.53
     Question
    0.53
     st
    0.53
    ázka
    0.52
     Ask
    0.50
     Choose
    0.50
     Fee
    0.50
     Rep
    0.49
     Centr
    0.48
    Activations Density 0.002%

    No Known Activations