© 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. 24-RES-MATRYOSHKA-DC
    7. 477
    Prev
    Next
    INDEX
    Explanations

    relationships or associations between different groups or countries

    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.24.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.24.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
     Gerais
    -0.60
     fédé
    -0.59
    sizeCache
    -0.58
    Thrift
    -0.57
     Inventors
    -0.57
    ErrorResponse
    -0.55
     sahiptir
    -0.54
    forRoot
    -0.54
    ienda
    -0.53
     bénévoles
    -0.53
    POSITIVE LOGITS
     diplomatic
    0.90
     international
    0.82
     diplomacy
    0.81
     diplomats
    0.79
     Iran
    0.78
     UN
    0.76
     Islamist
    0.76
     regime
    0.75
     NATO
    0.75
     military
    0.75
    Activations Density 2.777%

    No Known Activations