Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14437
    Prev
    Next
    INDEX
    Explanations

    references to a specific mathematical object or concept related to linear algebra and eigenvalues

    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
     Cor
    -0.94
     Kor
    -0.90
    Kor
    -0.77
     kor
    -0.65
     Кор
    -0.61
     Corinthians
    -0.57
     Kör
    -0.56
     KOR
    -0.55
     Coron
    -0.54
    zungs
    -0.53
    POSITIVE LOGITS
    cor
    1.95
    MigrationBuilder
    0.88
     contextLoads
    0.80
    expandindo
    0.79
     препратки
    0.78
    сылкі
    0.76
     gyhoeddwyd
    0.75
     дописавши
    0.73
     ―――――
    0.73
    tagHelperRunner
    0.72
    Activations Density 0.002%

    No Known Activations