© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6463
    Prev
    Next
    INDEX
    Explanations

    references to mathematical propositions and their numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.06
    Tikang
    -0.94
    Jereo
    -0.91
    новништво
    -0.85
     theorem
    -0.84
    QMetaType
    -0.83
    theorem
    -0.82
    tagHelperRunner
    -0.78
    setVerticalGroup
    -0.77
     facilité
    -0.75
    POSITIVE LOGITS
     Proposition
    2.70
    Proposition
    2.14
     proposition
    2.03
     propositions
    1.80
    proposition
    1.79
     Prop
    0.86
    Prop
    0.75
    prop
    0.55
     prop
    0.54
    Cal
    0.53
    Activations Density 0.007%

    No Known Activations