© 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. 5-CLT-HP
    7. 423
    Prev
    Next
    INDEX
    Explanations

    medical and technical language

    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
    setVerticalGroup
    -0.94
     متعلقه
    -0.74
    XmlAccessorType
    -0.69
     ujednoznacz
    -0.66
    yntaxException
    -0.64
    ThroughAttribute
    -0.60
    SpringBootTest
    -0.60
    $_['
    -0.59
    rawDesc
    -0.57
     ComVisible
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.51
     represents
    0.48
     represent
    0.48
     jsonArray
    0.46
     decisions
    0.46
     Represents
    0.45
     reps
    0.44
    práv
    0.43
    maj
    0.43
     Donnelly
    0.43
    Activations Density 0.003%

    No Known Activations