© 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. 92464
    Prev
    Next
    INDEX
    Explanations

    part

    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
    -1.25
    ſelf
    -1.06
    ſelves
    -1.03
     Majefty
    -1.02
     myſelf
    -1.01
     Reſ
    -1.00
     Jefus
    -0.99
     ſeveral
    -0.96
     Meksiku
    -0.96
     pleaſure
    -0.92
    POSITIVE LOGITS
     of
    1.68
    of
    0.77
     của
    0.70
    ของ
    0.70
     Of
    0.61
    Of
    0.60
    !
    0.57
    .
    0.56
     OF
    0.54
     for
    0.50
    Activations Density 0.016%

    No Known Activations