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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15626
    Prev
    Next
    INDEX
    Explanations

    references to other similar or placeholder objects or data structures in the text

    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
     riuscito
    -0.83
     figliu
    -0.75
     مشين
    -0.74
    ولايات
    -0.72
     sociaux
    -0.70
     volontà
    -0.69
     définiti
    -0.68
     célèbres
    -0.68
     chré
    -0.67
    chyma
    -0.67
    POSITIVE LOGITS
    other
    1.72
    OTHER
    1.38
    othermic
    0.80
    ther
    0.69
    Other
    0.67
    oth
    0.60
    othermal
    0.59
     Réponses
    0.57
    THER
    0.56
    otherapy
    0.56
    Activations Density 0.004%

    No Known Activations