© 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. 20-CLT-HP
    7. 74956
    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
     crawling
    -0.72
     Monfieur
    -0.63
     wrapping
    -0.62
     CURIAM
    -0.62
     crossed
    -0.62
     imprimée
    -0.61
     quantization
    -0.61
     profiling
    -0.59
     Efq
    -0.59
    craw
    -0.58
    POSITIVE LOGITS
     fill
    0.71
    fill
    0.66
     Fill
    0.60
     FILL
    0.57
     drain
    0.56
    StoryboardSegue
    0.55
     refill
    0.55
    FILL
    0.52
    Fill
    0.51
    ChildScrollView
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.