© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90773
    Prev
    Next
    INDEX
    Explanations

    P

    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
     Efq
    -1.07
     photolibrary
    -1.03
     crdi
    -1.03
     myſelf
    -1.03
     itſelf
    -1.02
     dreamstime
    -1.00
     ſeveral
    -0.98
     Shaksp
    -0.97
     ་་
    -0.97
     Sixt
    -0.97
    POSITIVE LOGITS
     or
    0.78
     can
    0.78
    .
    0.78
    ,
    0.76
    ↵↵
    0.75
     and
    0.73
     in
    0.73
    ↵
    0.68
     (
    0.68
     for
    0.67
    Activations Density 0.067%

    No Known Activations