© 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. 738
    Prev
    Next
    INDEX
    Explanations

    belief or conviction

    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
    encodeWith
    -0.55
     Мексичка
    -0.51
     heavily
    -0.49
    ones
    -0.49
    expandindo
    -0.48
     seriously
    -0.48
    RequestBody
    -0.47
     whether
    -0.44
    gulp
    -0.43
    tire
    -0.43
    POSITIVE LOGITS
    RetentionPolicy
    0.65
    InjectAttribute
    0.63
    saraba
    0.58
    ChildScrollView
    0.57
    satisfaction
    0.56
    ssysteme
    0.56
    OfWork
    0.55
    AddTagHelper
    0.54
     of
    0.54
    GeneratedValue
    0.54
    Activations Density 0.001%

    No Known Activations