© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7620
    Prev
    Next
    INDEX
    Explanations

    references to smoothness or smooth features in various contexts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Daun
    -0.67
    ukasz
    -0.64
     Vau
    -0.59
     Horton
    -0.59
    ukan
    -0.58
    JSONException
    -0.58
     sentry
    -0.58
    Kana
    -0.58
     setPassword
    -0.57
    XOR
    -0.57
    POSITIVE LOGITS
     smooth
    3.42
    smooth
    3.27
     Smooth
    3.27
    Smooth
    3.14
     smoothness
    2.66
     smoother
    2.55
     smoothly
    2.33
     lisse
    2.27
     smoothed
    2.23
     SMO
    2.03
    Activations Density 0.049%

    No Known Activations