© 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. 38611
    Prev
    Next
    INDEX
    Explanations

    bites

    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
     myſelf
    -1.37
     itſelf
    -1.36
     purpoſe
    -1.28
     ſche
    -1.26
     ſtate
    -1.26
     houſe
    -1.26
     Reſ
    -1.23
     greateſt
    -1.23
     Monfieur
    -1.23
     Jefus
    -1.23
    POSITIVE LOGITS
     in
    0.92
     and
    0.85
     (
    0.77
     the
    0.75
     as
    0.75
     all
    0.75
     a
    0.75
    ,
    0.73
     more
    0.72
     at
    0.71
    Activations Density 0.065%

    No Known Activations