© 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. 2547
    Prev
    Next
    INDEX
    Explanations

    statements indicating the conclusion or summary

    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
     final
    -1.01
    Final
    -1.01
    final
    -1.00
     Final
    -0.91
     FINAL
    -0.77
    FINAL
    -0.72
     Finals
    -0.70
    RectangleBorder
    -0.70
     finals
    -0.69
    ulemon
    -0.69
    POSITIVE LOGITS
     Finally
    2.69
    Finally
    2.55
     finally
    2.48
    finally
    2.48
     enfin
    2.16
     FINALLY
    1.99
     наконец
    1.95
     Enfin
    1.87
    Enfin
    1.84
     finalmente
    1.82
    Activations Density 0.019%

    No Known Activations