© 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. 1-CLT-HP
    7. 9363
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ]--;
    -0.58
    ">+
    -0.52
    PL
    -0.52
    >{"
    -0.50
    tify
    -0.50
    änd
    -0.50
     Cher
    -0.50
    ,))
    -0.49
     []),
    -0.48
    |)
    -0.48
    POSITIVE LOGITS
    TagMode
    0.81
    TintMode
    0.75
     للاسماء
    0.74
     financières
    0.74
    #+#
    0.72
    libft
    0.70
    elemField
    0.69
    @[+][
    0.68
     vectorielles
    0.67
     alimentaires
    0.67
    Activations Density 0.035%

    No Known Activations