© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72094
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Tembelea
    -0.72
    NameInMap
    -0.71
    principalTable
    -0.67
    ukone
    -0.67
     незавершена
    -0.67
    DockStyle
    -0.64
    IUrlHelper
    -0.63
    ніципалі
    -0.63
     EconPapers
    -0.63
    principalColumn
    -0.62
    POSITIVE LOGITS
     Dem
    0.47
     Le
    0.46
    compens
    0.43
     словарь
    0.42
    Dem
    0.40
     Wind
    0.40
     resto
    0.39
     Zong
    0.38
    "])
    0.38
     welfare
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.