© 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. 93632
    Prev
    Next
    INDEX
    Explanations

    Software development and design

    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
     designers
    -0.90
     designed
    -0.82
     designer
    -0.79
    designed
    -0.71
    DESIGN
    -0.70
     diseñador
    -0.68
     designs
    -0.67
     DESIGN
    -0.66
    Designed
    -0.66
    Design
    -0.66
    POSITIVE LOGITS
    }{*}{
    0.65
    ValueStyle
    0.56
     jLabel
    0.55
    GOTREF
    0.55
     nonatomic
    0.54
    WritableDatabase
    0.53
    zuführen
    0.52
    erializer
    0.52
     thiệu
    0.51
    agisse
    0.51
    Activations Density 0.192%

    No Known Activations