© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1109
    Prev
    Next
    INDEX
    Explanations

    the word "the" followed by words describing the nation, politics or demographics

    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
     gynhyrchwyd
    -0.55
    ใช่
    -0.54
    #![
    -0.50
    مية
    -0.48
    هما
    -0.47
    例の
    -0.44
    readValue
    -0.44
    Хьажоргаш
    -0.44
     handelt
    -0.43
     번째
    -0.43
    POSITIVE LOGITS
     masses
    0.90
     world
    0.87
     planète
    0.84
    masses
    0.80
     Wiktionnaire
    0.77
     globe
    0.77
    anskje
    0.75
     nation
    0.73
     planet
    0.73
     populace
    0.71
    Activations Density 1.278%

    No Known Activations