© 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. 5763
    Prev
    Next
    INDEX
    Explanations

    formality

    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
    ImageContext
    -0.61
    InstrumentedTest
    -0.61
    ValueStyle
    -0.57
    awtextra
    -0.54
    kach
    -0.52
    +#+#
    -0.52
    ActionEvent
    -0.51
    indd
    -0.48
    top
    -0.48
    참고
    -0.48
    POSITIVE LOGITS
     незавершена
    0.51
     enseignants
    0.48
    bootstrapcdn
    0.47
     variétés
    0.46
    venido
    0.46
    wpi
    0.45
    Portale
    0.45
    autaire
    0.45
     sumpay
    0.45
     NSCoder
    0.45
    Activations Density 0.006%

    No Known Activations