© 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. 45608
    Prev
    Next
    INDEX
    Explanations

    medical and scientific contexts

    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
    agu
    -0.62
    sch
    -0.50
    kle
    -0.45
    Label
    -0.42
    inkles
    -0.42
    sang
    -0.41
    the
    -0.41
    phi
    -0.41
    літ
    -0.40
    引
    -0.40
    POSITIVE LOGITS
     OFDb
    1.06
    WriteTagHelper
    1.03
     ModelExpression
    1.00
     <=",
    0.98
     дописавши
    0.96
     للمعارف
    0.94
    +:+
    0.93
     AssemblyVersion
    0.90
     hObject
    0.90
     للاسماء
    0.88
    Activations Density 0.373%

    No Known Activations