© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    product

    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
     product
    -0.60
    product
    -0.55
    Product
    -0.55
    rowsiness
    -0.55
     class
    -0.50
    3
    -0.44
     prodotto
    -0.42
    Not
    -0.42
     prodotti
    -0.41
    Class
    -0.40
    POSITIVE LOGITS
     Normdatei
    1.14
     unknownFields
    0.81
    脚注の使い方
    0.80
    MigrationBuilder
    0.78
    SequentialGroup
    0.73
    qxd
    0.72
     الحره
    0.71
    awaiter
    0.70
     snippetHide
    0.70
    hésite
    0.70
    Activations Density 0.032%

    No Known Activations