© 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. 12-RES-MATRYOSHKA-DC
    7. 3087
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to sets and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     שוליים
    -0.68
     BorderRadius
    -0.58
    存于互联网档案馆
    -0.49
     المعيارى
    -0.49
     ThemeData
    -0.49
    脚注の使い方
    -0.48
     חיצוניים
    -0.47
     cytometry
    -0.47
    backdrop
    -0.46
     Cytometry
    -0.46
    POSITIVE LOGITS
     azar
    0.57
    imab
    0.57
    ?,?,
    0.55
    Soorten
    0.55
    makeatletter
    0.54
     متعلقه
    0.54
    andExpect
    0.52
    zieć
    0.51
    wikimedia
    0.51
    vician
    0.51
    Activations Density 0.479%

    No Known Activations