© 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. 4-CLT-HP
    7. 331
    Prev
    Next
    INDEX
    Explanations

    image credits/URLs

    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
    ellites
    -0.49
     fourrure
    -0.43
    fallen
    -0.42
     enää
    -0.41
    liefer
    -0.41
    getConfiguration
    -0.41
     colegas
    -0.40
    <bos>
    -0.40
     keben
    -0.40
    äischen
    -0.39
    POSITIVE LOGITS
    DoubleQuotes
    0.94
    AndEndTag
    0.82
    Vidite
    0.72
     متعلقه
    0.72
    </tfoot>
    0.70
    ViewFeatures
    0.68
    +#+#
    0.68
     <=",
    0.68
    InputTagHelper
    0.68
    awtextra
    0.67
    Activations Density 0.014%

    No Known Activations