© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 377
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
     Wiktionnaire
    -0.76
     pleaſure
    -0.73
     Monfieur
    -0.71
    。。。
    -0.67
    {{/
    -0.66
     fubject
    -0.65
     ویکی‌پدی
    -0.64
     houſe
    -0.64
     épic
    -0.64
     ſeveral
    -0.64
    POSITIVE LOGITS
     &
    3.86
    &
    2.94
    )&
    2.56
    }&
    2.50
     \&
    2.44
    ,&
    2.36
     (&
    2.34
    ]&
    2.33
    (&
    2.30
    .&
    2.20
    Activations Density 0.225%

    No Known Activations