© 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. 834
    Prev
    Next
    INDEX
    Explanations

    Programming and blog-related texts

    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
     arrêt
    -0.51
    참고
    -0.50
    ownie
    -0.49
    Grazie
    -0.47
    grazie
    -0.47
    ிக்க
    -0.46
     tū
    -0.44
    허
    -0.44
     обнаружи
    -0.44
    有多
    -0.44
    POSITIVE LOGITS
    EDEFAULT
    0.82
    RectangleBorder
    0.76
    Geplaatst
    0.71
     Chwiliwch
    0.70
     فريبيس
    0.68
    principalTable
    0.65
    aarrggbb
    0.62
     Мексичка
    0.60
     she
    0.59
    pecto
    0.57
    Activations Density 0.000%

    No Known Activations