© 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. 2552
    Prev
    Next
    INDEX
    Explanations

    references to specific research funding sources and grant programs

    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
     moeite
    -0.92
     helft
    -0.76
     redenen
    -0.74
     vermogen
    -0.71
     omge
    -0.71
    houding
    -0.68
     uitzicht
    -0.68
     geïsole
    -0.67
     toekomst
    -0.66
     belangrij
    -0.65
    POSITIVE LOGITS
    heer
    0.70
    itie
    0.66
     AttributeSet
    0.64
    눔
    0.63
    CreateMap
    0.63
    Beschrijving
    0.61
     Nieuw
    0.61
    uur
    0.60
    sief
    0.58
    iteit
    0.57
    Activations Density 0.128%

    No Known Activations