© 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. 759
    Prev
    Next
    INDEX
    Explanations

    non-English words, with a focus on Italian, and numbers

    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
    ándolos
    -0.66
     Mongols
    -0.61
     entre
    -0.61
    WEBPACK
    -0.60
    |}{}
    -0.60
    ándola
    -0.58
    TestTools
    -0.56
    ArgumentParser
    -0.56
    ándonos
    -0.56
     morire
    -0.54
    POSITIVE LOGITS
     Questa
    0.57
     chrétien
    0.56
     françaises
    0.52
     già
    0.52
     Tutte
    0.51
     Mentre
    0.51
     européennes
    0.50
     américains
    0.50
     Secondo
    0.49
     présidenti
    0.49
    Activations Density 0.084%

    No Known Activations