© 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. 41183
    Prev
    Next
    INDEX
    Explanations

    names and medical mentions

    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
    ی
    -0.67
     Nelson
    -0.66
     Ed
    -0.59
    Nelson
    -0.54
    i
    -0.54
     broad
    -0.53
    y
    -0.48
    èze
    -0.47
    ised
    -0.46
     Broad
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.90
    IndentedString
    0.84
     defaultstate
    0.82
    WriteTagHelper
    0.79
    LookAnd
    0.75
    contentLoaded
    0.75
    tagHelperRunner
    0.72
    下载附件
    0.72
    WebVitals
    0.70
     nahilalakip
    0.70
    Activations Density 0.181%

    No Known Activations