© 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. 0-CLT-HP
    7. 43096
    Prev
    Next
    INDEX
    Explanations

    sure

    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
     sure
    -1.44
    sure
    -1.00
     realize
    -0.97
    Sure
    -0.93
     realized
    -0.91
     Sure
    -0.85
     SURE
    -0.78
     realizing
    -0.76
     realizes
    -0.73
     realised
    -0.68
    POSITIVE LOGITS
     <=",
    1.16
    makeConstraints
    0.89
    principalTable
    0.89
    (!__
    0.85
    UnusedPrivate
    0.83
     propOrder
    0.83
    RegistryLite
    0.82
    ItemBackground
    0.82
    Архівовано
    0.80
     незавершена
    0.79
    Activations Density 0.139%

    No Known Activations