© 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. 4-CLT-HP
    7. 5004
    Prev
    Next
    INDEX
    Explanations

    ranks and positions

    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
    highest
    -0.61
     lofty
    -0.58
    :✨
    -0.58
     highest
    -0.57
     lowest
    -0.55
    higher
    -0.51
    SerializedName
    -0.51
     seniors
    -0.50
    senior
    -0.50
     highs
    -0.50
    POSITIVE LOGITS
    GraphicsUnit
    0.66
    出版年
    0.61
    URUS
    0.60
    béco
    0.59
    Pranala
    0.55
    Abitanti
    0.54
     RADIUS
    0.52
    IFR
    0.52
    солю
    0.52
    Życiorys
    0.52
    Activations Density 0.003%

    No Known Activations