© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    food and agriculture

    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
    strix
    -0.47
     tombé
    -0.47
    bular
    -0.46
     "+
    -0.45
    carea
    -0.44
    tamol
    -0.44
    Rüyada
    -0.43
    KATH
    -0.43
    elang
    -0.43
     CreateTagHelper
    -0.43
    POSITIVE LOGITS
     martyrs
    0.75
     martyrdom
    0.73
     martyr
    0.72
     للاسماء
    0.71
     assassination
    0.70
     Phry
    0.69
     Upan
    0.68
     Prophe
    0.68
     Nautilus
    0.67
     Tacitus
    0.66
    Activations Density 0.024%

    No Known Activations