© 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. 5-CLT-HP
    7. 94294
    Prev
    Next
    INDEX
    Explanations

    revealing something

    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
     Theſe
    -0.86
     nahilalakip
    -0.84
     חיצוניים
    -0.77
    رشف
    -0.76
    Datuak
    -0.73
     Мексичка
    -0.72
     itſelf
    -0.71
    principalColumn
    -0.71
    UserScript
    -0.70
     NSCoder
    -0.70
    POSITIVE LOGITS
     in
    0.65
     for
    0.48
     cru
    0.47
     first
    0.46
     e
    0.45
     do
    0.44
     also
    0.42
    かは
    0.42
     both
    0.42
     estekak
    0.42
    Activations Density 0.003%

    No Known Activations