© 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. 0-CLT-HP
    7. 45128
    Prev
    Next
    INDEX
    Explanations

    proceedings

    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
     proceedings
    -1.88
     Proceedings
    -1.87
    Proceedings
    -1.66
     PROCEEDINGS
    -1.40
     Proceeding
    -1.28
     Proc
    -1.12
     proceeding
    -1.02
    Proc
    -0.96
    ceedings
    -0.85
    proc
    -0.74
    POSITIVE LOGITS
    olio
    0.54
     Universal
    0.50
     numerus
    0.48
    #+#
    0.48
    ViewStyle
    0.48
    keny
    0.47
     Packs
    0.46
    Autoritní
    0.46
     Hände
    0.45
     sức
    0.45
    Activations Density 1.723%

    No Known Activations