© 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. 2979
    Prev
    Next
    INDEX
    Explanations

    references to a specific historical or scholarly organization, specifically the "Commonwealth" and related heraldic or legal symbols

    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
    ViewFeatures
    -0.86
    dynam
    -0.83
     Cheney
    -0.73
    ollectionView
    -0.72
     يتيمه
    -0.71
    enumi
    -0.70
     Neum
    -0.68
    TargetException
    -0.68
    ไตล์
    -0.67
    帖最后由
    -0.67
    POSITIVE LOGITS
     naked
    0.74
     Naked
    0.73
     vapour
    0.71
    裸
    0.70
    TC
    0.68
    naked
    0.67
    Naked
    0.66
     TC
    0.66
    Raúl
    0.64
    IEEE
    0.61
    Activations Density 1.023%

    No Known Activations