© 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. 0-RES-MATRYOSHKA-DC
    7. 12093
    Prev
    Next
    INDEX
    Explanations

    references to contamination or polluted materials

    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
    脚注の使い方
    -0.91
    ThroughAttribute
    -0.67
    richTextPanel
    -0.67
    RegressionTest
    -0.66
     oprot
    -0.63
    saraba
    -0.60
    lossians
    -0.60
    ophyll
    -0.59
    tisgarh
    -0.57
    oa̍t
    -0.57
    POSITIVE LOGITS
     contaminated
    2.66
    contaminated
    1.92
     tainted
    1.37
     polluted
    1.30
     Conta
    1.27
     contaminate
    1.15
    tainted
    1.00
     contamin
    0.83
    Conta
    0.79
     poisoned
    0.77
    Activations Density 0.001%

    No Known Activations