© 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. 2674
    Prev
    Next
    INDEX
    Explanations

    references to varieties characterized by a wide range of options

    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
     expand
    -0.95
     Expanding
    -0.94
    Expansion
    -0.90
     Expand
    -0.87
     expanded
    -0.85
     Expansion
    -0.84
     expanding
    -0.84
    Expanding
    -0.82
     expansion
    -0.81
     expansions
    -0.79
    POSITIVE LOGITS
     wide
    2.38
    wide
    2.13
    Wide
    2.03
     Wide
    2.02
     WIDE
    1.89
    WIDE
    1.66
     širo
    1.08
     widest
    1.04
     tall
    1.02
     height
    0.88
    Activations Density 0.033%

    No Known Activations