© 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. 13248
    Prev
    Next
    INDEX
    Explanations

    nga

    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
    انيف
    -0.74
    وصلات
    -0.71
     Roskov
    -0.70
    nga
    -0.68
     initComponents
    -0.68
    Tikang
    -0.67
     esternos
    -0.67
     kaarangay
    -0.66
     purpoſe
    -0.65
    舺
    -0.64
    POSITIVE LOGITS
    oba
    0.56
     HasFactory
    0.54
     تضيفلها
    0.52
     '\\;'
    0.49
     fø
    0.47
    webpack
    0.45
     تن
    0.41
     form
    0.41
     Model
    0.40
     skj
    0.40
    Activations Density 0.013%

    No Known Activations