© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92953
    Prev
    Next
    INDEX
    Explanations

    Code and non-English

    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
     diaphragm
    -0.45
     “
    -0.38
     disini
    -0.38
    Essentially
    -0.37
    жы
    -0.37
     vending
    -0.36
     distanza
    -0.35
    кра
    -0.35
    اپ
    -0.35
    ’
    -0.35
    POSITIVE LOGITS
    DockStyle
    1.00
    RenderAtEndOf
    0.90
     onCancelled
    0.81
    ofire
    0.80
    SharedCtor
    0.77
    webElementXpaths
    0.76
    protoimpl
    0.75
    تفصیلات
    0.75
    Geplaatst
    0.72
     للاسماء
    0.72
    Activations Density 0.170%

    No Known Activations