© 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. 5-CLT-HP
    7. 2814
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
     pinulongan
    -0.57
    !).
    -0.54
     itſelf
    -0.53
     Shakspeare
    -0.52
    ConstraintMaker
    -0.52
    parsedMessage
    -0.51
    apunov
    -0.50
     Etrus
    -0.50
    loài
    -0.49
     Belén
    -0.48
    POSITIVE LOGITS
     Shots
    0.57
     Spot
    0.56
     Square
    0.56
     Lines
    0.55
     Rest
    0.54
     Side
    0.54
     Line
    0.54
     Common
    0.54
     Min
    0.54
     Days
    0.54
    Activations Density 0.043%

    No Known Activations