© 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. 7579
    Prev
    Next
    INDEX
    Explanations

    statements indicating that the neuron detects the presentation or derivation of mathematical or theoretical methods and their properties

    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
     nahilalakip
    -0.85
    StoryboardSegue
    -0.64
    /**
    -0.60
    GRect
    -0.59
     Gutenberg
    -0.59
     Wikimedijinoj
    -0.59
     AttributeSet
    -0.59
    DataURL
    -0.58
    urtstag
    -0.56
     Vulcan
    -0.56
    POSITIVE LOGITS
    駁
    0.63
    createTextNode
    0.60
    providedIn
    0.57
     explications
    0.56
     Chwiliwch
    0.55
     giải
    0.51
     explained
    0.50
    trieb
    0.50
     beno
    0.49
     مشين
    0.49
    Activations Density 0.811%

    No Known Activations