© 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. 20-CLT-HP
    7. 74694
    Prev
    Next
    INDEX
    Explanations

    Technical discussions

    np_max-act-logits · 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
     '\\;'
    -0.60
     calendriers
    -0.51
    ună
    -0.51
    [++
    -0.49
     Bartholo
    -0.47
    Presentation
    -0.47
    Tazama
    -0.46
    ollectionView
    -0.45
     ditu
    -0.45
     Bemer
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    MessageTagHelper
    0.72
     مرئيه
    0.67
    Dixie
    0.59
    ClientRect
    0.59
     ModelExpression
    0.56
    WebVitals
    0.54
    TagHelpers
    0.54
    DBNull
    0.54
     NavController
    0.51
    Activations Density 0.000%

    No Known Activations