© 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. 7717
    Prev
    Next
    INDEX
    Explanations

    references to complex mathematical formulas and concepts related to proofs, ideals, and algebraic structures

    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
     label
    -1.61
     Label
    -1.59
     labels
    -1.54
     Labels
    -1.41
     LABEL
    -1.38
    label
    -1.34
     labeling
    -1.31
    labels
    -1.30
    Label
    -1.30
     labelling
    -1.25
    POSITIVE LOGITS
    ἴ
    0.54
     ſen
    0.51
    Final
    0.50
    par
    0.49
    Fus
    0.48
     ſta
    0.48
    way
    0.47
     fallecimiento
    0.47
    final
    0.47
     CORT
    0.45
    Activations Density 0.056%

    No Known Activations