© 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. 41180
    Prev
    Next
    INDEX
    Explanations

    scientific/medical 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
     degree
    -0.75
     ویکی‌پدیای
    -0.59
     câbles
    -0.59
    IBarButtonItem
    -0.57
    degree
    -0.56
     Degree
    -0.56
     Rasmus
    -0.54
     degrés
    -0.53
    =$?
    -0.53
    lasma
    -0.53
    POSITIVE LOGITS
    fjspx
    0.71
     CreateTagHelper
    0.63
     chi̍t
    0.62
    modelBuilder
    0.59
    TagMode
    0.56
    AddTagHelper
    0.51
     progres
    0.50
     progression
    0.48
    :✨
    0.47
    EndInit
    0.47
    Activations Density 0.045%

    No Known Activations