© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2590
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    Hentet
    -0.72
     mariée
    -0.69
    IUrlHelper
    -0.59
     Rollo
    -0.58
     initComponents
    -0.57
     ivelany
    -0.56
    <()>
    -0.56
     BorderSide
    -0.56
     мәкал
    -0.55
     bå
    -0.54
    POSITIVE LOGITS
     are
    0.56
     continue
    0.52
     were
    0.48
     have
    0.47
     benefit
    0.46
     provide
    0.46
     charged
    0.46
     aren
    0.45
    PROV
    0.45
     promote
    0.45
    Activations Density 0.003%

    No Known Activations