© 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. 0-CLT-HP
    7. 1963
    Prev
    Next
    INDEX
    Explanations

    Medical studies/trials

    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
     trials
    -0.95
    expandindo
    -0.83
    protoimpl
    -0.76
     quæ
    -0.75
    GEBURTSDATUM
    -0.75
     Monfieur
    -0.73
     bogotá
    -0.73
     Reſ
    -0.71
    Trials
    -0.70
     sandero
    -0.70
    POSITIVE LOGITS
     near
    0.50
     worth
    0.48
     AssemblyTitle
    0.48
    ViewInit
    0.47
    ناصر
    0.47
    ClientRect
    0.46
     super
    0.44
    ؤية
    0.44
     effective
    0.43
    îtra
    0.43
    Activations Density 0.047%

    No Known Activations