© 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. 5-CLT-HP
    7. 93237
    Prev
    Next
    INDEX
    Explanations

    e.g

    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
    astă
    -0.49
     useNavigate
    -0.46
     outside
    -0.43
    -0.43
    OUTSIDE
    -0.42
    省市镇
    -0.41
     استنادى
    -0.41
     now
    -0.41
     vagues
    -0.40
    āci
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.76
    
    0.72
    Hochspringen
    0.70
     EconPapers
    0.65
     nakalista
    0.65
    .,
    0.64
    AutoScale
    0.64
     ligiloj
    0.63
    Odkazy
    0.61
     cherchés
    0.60
    Activations Density 0.003%

    No Known Activations