© 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. 5668
    Prev
    Next
    INDEX
    Explanations

    Generic English text

    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
     >=",
    -0.66
     typelib
    -0.56
    těte
    -0.54
    TProtocol
    -0.54
     Jefus
    -0.52
     properly
    -0.52
     Meters
    -0.52
    MLLoader
    -0.51
    setVerticalGroup
    -0.51
    FTFY
    -0.50
    POSITIVE LOGITS
    queryInterface
    0.69
    例句
    0.59
    tagHelperRunner
    0.57
    inkan
    0.54
     venons
    0.52
    ьаж
    0.50
    ಂಡ
    0.47
    principalColumn
    0.46
     pozor
    0.46
     envió
    0.45
    Activations Density 0.001%

    No Known Activations