© 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. 1568
    Prev
    Next
    INDEX
    Explanations

    references to natural substances or processes

    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
    ValueStyle
    -0.62
    ScopeManager
    -0.59
    BoxShadow
    -0.57
    addContainerGap
    -0.56
    entious
    -0.56
     Spez
    -0.53
    CaseSensitive
    -0.52
     đại
    -0.52
     noDo
    -0.52
     Toujours
    -0.52
    POSITIVE LOGITS
     natural
    4.81
    natural
    4.53
    Natural
    4.50
     Natural
    4.44
     NATURAL
    4.13
    NATURAL
    3.98
     naturale
    3.67
     naturelle
    3.55
     naturales
    3.53
     naturel
    3.50
    Activations Density 0.670%

    No Known Activations