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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14716
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific type of matrix transformation, particularly those with high orthogonality or particular code properties used in error correction and data security

    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
    reportWebVitals
    -0.71
     Azo
    -0.63
    omitempty
    -0.59
     링크
    -0.59
    DMETHOD
    -0.59
    fromnode
    -0.57
    Ribbon
    -0.55
     Cæsar
    -0.55
     Atlético
    -0.55
     Hornet
    -0.55
    POSITIVE LOGITS
     RO
    2.16
     Paglinawan
    0.64
     feast
    0.60
     Rolling
    0.60
     roulant
    0.59
     Ro
    0.57
     Roots
    0.57
     roule
    0.56
     متعلقه
    0.56
    SharedCtor
    0.55
    Activations Density 0.008%

    No Known Activations