© 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. 5-CLT-HP
    7. 92649
    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
     Vikipedi
    -0.49
    انجليز
    -0.48
    rspec
    -0.47
    lati
    -0.47
    Semana
    -0.46
     ad
    -0.45
    اح
    -0.45
    CategoryName
    -0.44
     Her
    -0.43
     Ad
    -0.42
    POSITIVE LOGITS
     Italijanski
    0.85
    Референце
    0.84
     autorytatywna
    0.81
    /**
    0.79
     Paglinawan
    0.73
     שוליים
    0.72
    ьаж
    0.70
     fucks
    0.66
     BoxDecoration
    0.65
    GraphicsUnit
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.