© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76991
    Prev
    Next
    INDEX
    Explanations

    Technical and code related text

    np_max-act-logits · 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
    ConstraintMaker
    -1.01
     cherchés
    -0.99
     snippetHide
    -0.93
     "..\..\..\
    -0.93
    ValueStyle
    -0.90
     ویکی‌پدی
    -0.89
     ویکی‌پدیای
    -0.87
     Autorizaciones
    -0.86
     eventdata
    -0.85
     Smaller
    -0.84
    POSITIVE LOGITS
     hard
    0.47
     straight
    0.44
     do
    0.39
    i
    0.39
    ο
    0.37
    <?
    0.34
    re
    0.34
    ев
    0.34
    erschrank
    0.34
     simple
    0.34
    Activations Density 0.000%

    No Known Activations