© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11750
    Prev
    Next
    INDEX
    Explanations

    medical conditions/pregnancy

    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
    <bos>
    -0.78
     sauvages
    -0.71
     iniziale
    -0.63
     blessé
    -0.61
     disparu
    -0.59
     registrazione
    -0.57
     copertura
    -0.57
     rekke
    -0.56
     Grecs
    -0.56
     vectorielles
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.70
    TypedDataSet
    0.69
    SequentialGroup
    0.68
     newOwner
    0.68
    ConverterFactory
    0.68
    parsedMessage
    0.66
    AutoField
    0.65
     resourceCulture
    0.65
    DeleteBehavior
    0.64
    ///</
    0.63
    Activations Density 0.044%

    No Known Activations