© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10507
    Prev
    Next
    INDEX
    Explanations

    punctuation and discourse markers

    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
     myſelf
    -0.63
     Efq
    -0.62
     itſelf
    -0.60
     such
    -0.59
     caviar
    -0.58
     dates
    -0.57
     becauſe
    -0.56
     rodríguez
    -0.56
     spheres
    -0.55
     turbidity
    -0.55
    POSITIVE LOGITS
     The
    0.81
     A
    0.69
     You
    0.66
     We
    0.60
    "
    0.59
     côtés
    0.56
     There
    0.56
     It
    0.56
     An
    0.56
     By
    0.54
    Activations Density 0.299%

    No Known Activations