© 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. 2648
    Prev
    Next
    INDEX
    Explanations

    references to specific authoritative or official sources

    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
    provide
    -0.97
     Provide
    -0.96
     provide
    -0.94
     provides
    -0.92
    Provide
    -0.92
     providing
    -0.92
    Provides
    -0.91
     Provides
    -0.91
     Providing
    -0.88
    provides
    -0.88
    POSITIVE LOGITS
     given
    2.45
     Given
    2.36
    Given
    2.25
    given
    2.14
     GIVEN
    1.94
     dado
    1.42
     dadas
    1.30
     dada
    1.27
    Dado
    1.19
     Dado
    1.09
    Activations Density 0.128%

    No Known Activations