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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74637
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     كومونز
    -0.70
    @[+][
    -0.63
    いき
    -0.61
     الحره
    -0.60
    ressum
    -0.59
    RTLD
    -0.57
    AsUp
    -0.56
     From
    -0.56
     Judges
    -0.54
    addPreferredGap
    -0.54
    POSITIVE LOGITS
    invokeLater
    0.61
     chaff
    0.43
    новништво
    0.42
     also
    0.40
     stencil
    0.38
    WebServlet
    0.38
     foots
    0.38
     createState
    0.38
    UVWXYZ
    0.36
     /\.(
    0.36
    Activations Density 0.012%

    No Known Activations