© 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. 0-CLT-HP
    7. 97074
    Prev
    Next
    INDEX
    Explanations

    finance, technology, legal

    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
    Ether
    -0.46
     sa
    -0.43
    pe
    -0.43
    esto
    -0.40
    urka
    -0.40
    lot
    -0.40
     подска
    -0.40
    Requires
    -0.40
    ph
    -0.39
     cu
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    1.27
     utafitiHapana
    1.08
     defaultstate
    1.05
    tagHelperRunner
    1.02
    تقاوى
    1.01
    )");
    1.01
     فريبيس
    0.97
     "..\..\..\
    0.93
     виправивши
    0.93
    MigrationBuilder
    0.93
    Activations Density 0.385%

    No Known Activations