© 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. 22-RES-MATRYOSHKA-DC
    7. 1719
    Prev
    Next
    INDEX
    Explanations

    mentions of formal titles and institutions, particularly those related to government and academia, often in the UK.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guam
    -0.60
    BagConstraints
    -0.59
     везе
    -0.59
    msgTypes
    -0.56
    inigte
    -0.54
     виправивши
    -0.54
    Aloha
    -0.53
     Baillargeon
    -0.53
     ImageIcon
    -0.52
    ThroughAttribute
    -0.52
    POSITIVE LOGITS
     London
    1.79
     British
    1.77
     UK
    1.71
     Britain
    1.66
    London
    1.63
     England
    1.62
    British
    1.57
     £
    1.51
     LONDON
    1.50
    Britain
    1.48
    Activations Density 2.284%

    No Known Activations