© 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. 1-CLT-HP
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    medical/scientific/technical texts

    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
     propOrder
    -0.78
    MigrationBuilder
    -0.76
    WireFormatLite
    -0.65
    enterOuterAlt
    -0.65
    الإنجليزية
    -0.63
     endforeach
    -0.60
    Przypisy
    -0.60
    MessageOf
    -0.60
    AsUp
    -0.59
     insuffisamment
    -0.57
    POSITIVE LOGITS
    withIdentifier
    0.54
    WithIdentifier
    0.52
     Include
    0.49
    phrine
    0.49
    TagHelper
    0.48
     bezeichneter
    0.47
    sendKeys
    0.47
     attributable
    0.45
     Abteilung
    0.45
     Ebola
    0.44
    Activations Density 0.060%

    No Known Activations