© 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. 472
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation used to denote patents and figures

    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
    مصادر
    -0.65
     famí
    -0.64
    DoubleQuotes
    -0.57
    ۱
    -0.56
    ValueStyle
    -0.55
    -------------</
    -0.54
    SequentialGroup
    -0.53
    خبار
    -0.52
     typelib
    -0.49
    stwo
    -0.49
    POSITIVE LOGITS
     thousand
    1.05
     thousands
    1.01
     Thousands
    0.86
    thousand
    0.84
    thousands
    0.80
     THOUS
    0.79
    Thousands
    0.78
     millions
    0.76
    Thousand
    0.71
     Thousand
    0.68
    Activations Density 4.217%

    No Known Activations