© 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. 3511
    Prev
    Next
    INDEX
    Explanations

    references to scientific research or scholarly information

    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
     Science
    -0.94
    Science
    -0.82
     termica
    -0.80
     SCIENCE
    -0.77
     EconPapers
    -0.75
     science
    -0.69
     Sciences
    -0.68
    Література
    -0.62
    science
    -0.61
     SCIENCES
    -0.60
    POSITIVE LOGITS
     Scientific
    2.41
    Scientific
    2.27
     scientific
    2.17
     SCIENTIFIC
    2.08
    scientific
    2.03
    cientific
    1.55
     scienti
    1.34
     scientifically
    1.30
     Scienti
    1.27
     científica
    1.23
    Activations Density 0.020%

    No Known Activations