© 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. 1-CLT-HP
    7. 46305
    Prev
    Next
    INDEX
    Explanations

    ran

    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
     infine
    -0.49
     veren
    -0.48
    AndEndTag
    -0.48
     inoltre
    -0.46
    yors
    -0.44
     zwart
    -0.44
     خواهند
    -0.44
    ện
    -0.43
     siyah
    -0.42
     peores
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.98
     تضيفلها
    0.92
     ModelExpression
    0.85
     للاسماء
    0.84
    AddHtmlAttribute
    0.83
    OGND
    0.82
    AddTagHelper
    0.79
     noDo
    0.74
    Gambas
    0.74
     estimés
    0.73
    Activations Density 0.042%

    No Known Activations