© 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. 2-RES-MATRYOSHKA-DC
    7. 6866
    Prev
    Next
    INDEX
    Explanations

    references to contamination or pollution

    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
    phosa
    -0.69
     cera
    -0.64
    lora
    -0.64
    PerformLayout
    -0.62
    readystatechange
    -0.61
     JsonObject
    -0.60
    Predecesor
    -0.59
    mphony
    -0.58
     newline
    -0.58
    Gweler
    -0.57
    POSITIVE LOGITS
     contamination
    2.81
     Contamination
    2.45
     contaminated
    2.42
     contamin
    2.39
    contamination
    2.25
     contaminate
    2.23
     contaminants
    2.22
    contaminated
    2.19
     contaminant
    2.05
     Contamin
    1.92
    Activations Density 0.007%

    No Known Activations