© 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. 4-CLT-HP
    7. 3061
    Prev
    Next
    INDEX
    Explanations

    Medical/Coding

    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
    codegen
    -0.45
    <?
    -0.43
     of
    -0.43
     years
    -0.42
     material
    -0.41
    ree
    -0.41
     القرن
    -0.39
    achelor
    -0.39
    백
    -0.37
    SystemColors
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    0.93
     فريبيس
    0.77
    ThroughAttribute
    0.77
    UnsafeEnabled
    0.74
    ValueStyle
    0.74
    AndEndTag
    0.71
    Билгалдахарш
    0.70
    StructEnd
    0.70
    IsContent
    0.69
     ProtoMessage
    0.68
    Activations Density 0.002%

    No Known Activations