© 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. 4-CLT-HP
    7. 2753
    Prev
    Next
    INDEX
    Explanations

    Indian

    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
    makeConstraints
    -0.71
     femininas
    -0.69
     normaux
    -0.66
    UserScript
    -0.64
     استنادى
    -0.64
     cherchés
    -0.61
     juſ
    -0.60
    apunov
    -0.58
     perſon
    -0.57
     risorse
    -0.57
    POSITIVE LOGITS
    
    0.52
    DoubleQuotes
    0.47
     Cras
    0.45
    fsen
    0.45
     dataSnapshot
    0.45
    Rhestr
    0.43
    UD
    0.42
     converge
    0.42
    หร
    0.42
    tagHelperRunner
    0.40
    Activations Density 0.009%

    No Known Activations