© 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. 0-CLT-HP
    7. 41579
    Prev
    Next
    INDEX
    Explanations

    Medical and interpretive 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
     vastaan
    -0.57
     cloth
    -0.56
     Cloth
    -0.56
    ValueStyle
    -0.55
    TintMode
    -0.54
     bakom
    -0.54
    readAs
    -0.54
     lumières
    -0.53
     ricev
    -0.52
     hindurch
    -0.52
    POSITIVE LOGITS
    XmlEnum
    0.57
    SuppressMessage
    0.54
    s
    0.54
    ttemberg
    0.50
    __*/
    0.50
    featureID
    0.48
     kasarigan
    0.47
    ]-->
    0.47
    ful
    0.47
     protoimpl
    0.47
    Activations Density 0.034%

    No Known Activations