© 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. 189
    Prev
    Next
    INDEX
    Explanations

    locations or national origin

    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
     lenker
    -0.71
     Roskov
    -0.71
    enderror
    -0.65
    ViewImports
    -0.64
    AccessorTable
    -0.63
    حوالہ
    -0.62
    はじめに
    -0.58
     étions
    -0.57
    сылкі
    -0.57
     incomplète
    -0.56
    POSITIVE LOGITS
     government
    0.82
     nationals
    0.76
     national
    0.72
     citizens
    0.69
     Government
    0.69
     National
    0.69
     law
    0.67
    orszá
    0.64
     cities
    0.63
     legislature
    0.63
    Activations Density 1.599%

    No Known Activations