© 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. 1-RES-MATRYOSHKA-DC
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    references to distinct or individual units or entities

    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
    WebControls
    -0.69
     Various
    -0.61
     Preferencias
    -0.57
     various
    -0.56
    Various
    -0.56
    various
    -0.55
     AssemblyProduct
    -0.55
    inafter
    -0.53
     diversos
    -0.52
     diverses
    -0.51
    POSITIVE LOGITS
     Separate
    3.59
     separate
    3.58
    separate
    3.53
     SEPAR
    3.52
    Separate
    3.50
     Separ
    3.48
     separated
    3.33
    separ
    3.20
     separation
    3.19
     separates
    3.17
    Activations Density 0.504%

    No Known Activations