© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3591
    Prev
    Next
    INDEX
    Explanations

    mail and package delivery

    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
     of
    -0.46
     springfox
    -0.43
    =|
    -0.43
    Personensuche
    -0.42
     спорт
    -0.41
    styleType
    -0.41
    gadier
    -0.41
    Abend
    -0.40
    eren
    -0.40
    \"");
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    0.76
     Réponses
    0.75
    uxxxx
    0.74
    FormTagHelper
    0.72
    aarrggbb
    0.70
    RegressionTest
    0.69
     houſe
    0.69
    MessageTagHelper
    0.68
    tagHelperRunner
    0.66
     itſelf
    0.66
    Activations Density 0.007%

    No Known Activations