© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    references to theft or stolen property

    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
     Kün
    -0.60
     estekak
    -0.58
    netje
    -0.57
    reportWebVitals
    -0.56
     ICF
    -0.55
     iconFacebook
    -0.54
     Kombat
    -0.53
    IVersion
    -0.53
     suất
    -0.52
    Zeneca
    -0.52
    POSITIVE LOGITS
     theft
    2.84
     stolen
    2.67
     steal
    2.47
     stealing
    2.45
     thefts
    2.45
     stole
    2.41
     Theft
    2.41
     thief
    2.39
     thieves
    2.34
    theft
    2.34
    Activations Density 0.060%

    No Known Activations