© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13073
    Prev
    Next
    INDEX
    Explanations

    the presence of specific mathematically defined structures or properties

    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
     ویکی‌پدیا
    -0.70
     ranks
    -0.57
     rank
    -0.55
     skimage
    -0.51
    ományos
    -0.51
    来得
    -0.50
    clusal
    -0.50
     galeria
    -0.50
    Kaynakça
    -0.49
    strokeWidth
    -0.49
    POSITIVE LOGITS
    rank
    2.27
    ran
    0.70
     Crank
    0.67
    })));
    0.65
    UnusedPrivate
    0.65
    RunAsync
    0.63
    RenderAtEndOf
    0.62
    RANK
    0.61
    }))
    0.60
    UnknownFields
    0.60
    Activations Density 0.006%

    No Known Activations