© 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. 46300
    Prev
    Next
    INDEX
    Explanations

    shape

    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
    析
    -0.50
     evidences
    -0.47
     stream
    -0.45
     şek
    -0.45
     streaming
    -0.44
    форми
    -0.43
     level
    -0.43
     leve
    -0.43
     نامه
    -0.43
     form
    -0.42
    POSITIVE LOGITS
     Мексичка
    0.90
    بوابة
    0.82
    tagHelperRunner
    0.75
    
    0.70
    enumi
    0.69
    uesia
    0.68
    +#+#
    0.67
    endphp
    0.66
     estekak
    0.65
    NavController
    0.63
    Activations Density 0.077%

    No Known Activations