© 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. 90946
    Prev
    Next
    INDEX
    Explanations

    Glycosylation and scientific terms

    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
    neſs
    -0.91
     Efq
    -0.90
    alities
    -0.88
    ality
    -0.87
     purpoſe
    -0.86
    ſelves
    -0.86
    ſelf
    -0.85
    ership
    -0.84
     Majefty
    -0.83
    IZATION
    -0.82
    POSITIVE LOGITS
    execSQL
    0.50
    !
    0.50
    ː
    0.50
    e
    0.49
    liki
    0.48
     gained
    0.47
    ba
    0.47
    例句
    0.47
    .
    0.46
     interpreted
    0.46
    Activations Density 1.554%

    No Known Activations