© 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. 5-CLT-HP
    7. 91783
    Prev
    Next
    INDEX
    Explanations

    sandwiches

    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
    Архівовано
    -0.46
    gatsby
    -0.42
    رشف
    -0.42
     Réponses
    -0.42
    BoxShadow
    -0.40
     ویکی‌پدیا
    -0.40
     PropTypes
    -0.40
     pessoal
    -0.39
     democrática
    -0.38
    丁目
    -0.38
    POSITIVE LOGITS
     "..\..\
    0.81
    المناصب
    0.74
     "..\..\..\
    0.71
     parlour
    0.63
     referenties
    0.63
     Wikimedijinoj
    0.62
    sbericht
    0.62
    évaluateur
    0.61
    tagext
    0.60
     jScrollPane
    0.60
    Activations Density 0.001%

    No Known Activations