© 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. 1694
    Prev
    Next
    INDEX
    Explanations

    math symbols and notation, especially those using dollar signs

    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
     poulet
    -0.44
    onyme
    -0.42
    twimg
    -0.42
    uws
    -0.42
    couz
    -0.40
     Winaray
    -0.39
    ContentAsync
    -0.38
    ⓘ
    -0.37
     geleverd
    -0.36
    gaard
    -0.35
    POSITIVE LOGITS
     b
    1.23
     B
    1.20
    b
    1.09
    B
    1.08
     б
    0.94
    getB
    0.90
    bB
    0.89
     bpy
    0.87
     Bb
    0.86
    ｂ
    0.83
    Activations Density 2.762%

    No Known Activations