© 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. 22-RES-MATRYOSHKA-DC
    7. 1912
    Prev
    Next
    INDEX
    Explanations

    a variety of numeric data, including ranges, version like numbers, temperatures, and other code block related 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
     almost
    -0.81
    almost
    -0.68
     Almost
    -0.66
     hampir
    -0.65
    Almost
    -0.62
     nearly
    -0.61
     casi
    -0.61
     почти
    -0.56
    imp
    -0.55
     prawie
    -0.54
    POSITIVE LOGITS
    Ten
    1.05
     Ten
    1.05
     ten
    1.05
     TEN
    0.91
     fifty
    0.82
     dizaine
    0.77
     Fifty
    0.75
     kym
    0.75
     dieci
    0.75
     zehn
    0.73
    Activations Density 1.917%

    No Known Activations