© 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. 0-CLT-HP
    7. 40463
    Prev
    Next
    INDEX
    Explanations

    pain

    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
    i
    -1.52
     spray
    -1.02
    ache
    -1.00
    a
    -0.93
    n
    -0.85
    ACHE
    -0.82
     i
    -0.75
    l
    -0.73
     Spray
    -0.72
    t
    -0.72
    POSITIVE LOGITS
     itſelf
    1.47
     Efq
    1.46
     myſelf
    1.42
    ſelf
    1.32
     themſelves
    1.27
    oredCriteria
    1.27
     Jefus
    1.20
     greateſt
    1.20
     himſelf
    1.17
     ſeveral
    1.15
    Activations Density 0.527%

    No Known Activations