© 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. 5-CLT-HP
    7. 96792
    Prev
    Next
    INDEX
    Explanations

    short

    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
    IUrlHelper
    -0.62
     nahilalakip
    -0.59
     isNameExpr
    -0.57
    GeneratedCode
    -0.52
    marshaller
    -0.52
    ffindor
    -0.52
    contentLoaded
    -0.50
     InputDecoration
    -0.50
     poliuret
    -0.50
    multirow
    -0.50
    POSITIVE LOGITS
     note
    0.77
     Note
    0.65
     Reminder
    0.61
     Stroll
    0.60
     recap
    0.59
    pensive
    0.58
     overview
    0.57
     cliquez
    0.57
     notice
    0.56
     reminder
    0.56
    Activations Density 0.091%

    No Known Activations