© 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. 398
    Prev
    Next
    INDEX
    Explanations

    references to specific entities, particularly organizations, laws, or individuals

    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
     loob
    -0.63
     Chwiliwch
    -0.60
     fure
    -0.58
    extAlignment
    -0.58
     for
    -0.55
    grao
    -0.52
    Chham
    -0.52
     Oilers
    -0.51
     אית
    -0.51
     hjemme
    -0.50
    POSITIVE LOGITS
     by
    3.19
    by
    2.66
     By
    2.52
     BY
    2.48
    By
    2.44
     oleh
    2.44
    BY
    2.08
    bys
    1.88
     توسط
    1.85
    mby
    1.69
    Activations Density 0.700%

    No Known Activations