© 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. 677
    Prev
    Next
    INDEX
    Explanations

    mathematical or physics equations and related terms with high activation, and possibly recognizing text formatting like section headers

    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
     informée
    -0.72
     CreateTagHelper
    -0.70
    ///</
    -0.67
    InitVars
    -0.67
    الحياه
    -0.67
    awtextra
    -0.65
    iseries
    -0.65
     समीक्षाओं
    -0.65
     propOrder
    -0.63
    setopt
    -0.62
    POSITIVE LOGITS
     particles
    0.69
     particle
    0.55
    lichung
    0.55
     Particles
    0.54
     quanta
    0.52
     fermions
    0.52
    Демо
    0.49
    粒
    0.49
     PARTIC
    0.48
     carriers
    0.48
    Activations Density 0.795%

    No Known Activations