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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73465
    Prev
    Next
    INDEX
    Explanations

    ant prefix

    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
    uel
    -0.59
     eventdata
    -0.50
     lipca
    -0.49
    ค์
    -0.47
    Xaml
    -0.45
    ues
    -0.45
     SwiftUI
    -0.44
    ULUS
    -0.44
    ulus
    -0.43
    ęs
    -0.43
    POSITIVE LOGITS
     Tapatalk
    0.57
     Мексичка
    0.57
     Autorisations
    0.56
     itſelf
    0.55
    GEBURTS
    0.55
    ennas
    0.55
    Datuak
    0.54
     Torna
    0.54
     سكانية
    0.53
     NDEBUG
    0.52
    Activations Density 0.007%

    No Known Activations