© 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. 2-RES-MATRYOSHKA-DC
    7. 4807
    Prev
    Next
    INDEX
    Explanations

    mentions of key political figures, institutions, and scandals related to corruption investigations

    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
    StreetMap
    -0.85
     Emin
    -0.73
     Lala
    -0.71
     Bing
    -0.70
     Jama
    -0.68
     disponibilités
    -0.68
     Pash
    -0.68
    |')
    -0.66
     Ems
    -0.66
    Freezing
    -0.65
    POSITIVE LOGITS
     Portfolio
    0.79
     Brasilien
    0.75
     vernis
    0.75
    multer
    0.74
     portfolio
    0.72
    Portfolio
    0.71
     Pollack
    0.71
     Portuguese
    0.68
     brasile
    0.68
     portug
    0.68
    Activations Density 1.583%

    No Known Activations