© 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. 803
    Prev
    Next
    INDEX
    Explanations

    locations, place names, areas, and 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
    возь
    -0.50
    havior
    -0.49
     Yellowstone
    -0.49
    kaper
    -0.47
    antd
    -0.46
     Preferencias
    -0.45
    Lietu
    -0.44
    λό
    -0.44
    oa̍t
    -0.43
     Hanford
    -0.43
    POSITIVE LOGITS
     Arabic
    0.99
     Arab
    0.94
     Egyptian
    0.91
     Cairo
    0.84
     Ramadan
    0.82
     Egypt
    0.81
     Arabs
    0.81
     Saudi
    0.81
    Arab
    0.80
    Cairo
    0.79
    Activations Density 0.693%

    No Known Activations