© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39791
    Prev
    Next
    INDEX
    Explanations

    The

    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
     aéri
    -0.50
     humain
    -0.50
     AssemblyCompany
    -0.47
     chers
    -0.46
     adesivo
    -0.46
     Atra
    -0.45
     Guna
    -0.45
     Herod
    -0.44
    יות
    -0.43
     Justo
    -0.43
    POSITIVE LOGITS
     snippetHide
    1.02
    AddTagHelper
    0.86
     ModelExpression
    0.83
     Мексичка
    0.77
    LikeLiked
    0.75
     typelib
    0.73
     المعيارى
    0.73
    styleType
    0.71
    ConstraintMaker
    0.71
    WriteTagHelper
    0.71
    Activations Density 0.337%

    No Known Activations