© 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. 20-CLT-HP
    7. 71721
    Prev
    Next
    INDEX
    Explanations

    MD

    np_max-act-logits · 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
    GEBURTSDATUM
    -0.67
    Geplaatst
    -0.65
    LookAnd
    -0.63
     nahilalakip
    -0.63
    MigrationBuilder
    -0.59
     estimés
    -0.57
     wrongly
    -0.57
     incorrectly
    -0.57
     Assumptions
    -0.56
    Assumptions
    -0.56
    POSITIVE LOGITS
    ########.
    0.61
    AnchorStyles
    0.61
    findpost
    0.51
     ostavi
    0.49
    +#+#
    0.48
    ContentLoaded
    0.48
     mojej
    0.48
    tableFuture
    0.48
     "..\..\
    0.46
    CDATA
    0.46
    Activations Density 0.002%

    No Known Activations