© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, formulas, and common mathematical expressions

    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
    存于互联网档案馆
    -0.68
    TemporalType
    -0.60
    abestanden
    -0.59
    ViewImports
    -0.58
    UniformLocation
    -0.56
    satis
    -0.55
     newOwner
    -0.53
    anmoins
    -0.52
     hereinafter
    -0.51
     Jurí
    -0.51
    POSITIVE LOGITS
    发表于
    0.64
     induction
    0.60
    hypothesis
    0.57
     hypothesis
    0.56
     assumption
    0.55
    induction
    0.54
     claim
    0.51
     Claim
    0.51
    issage
    0.50
     assertion
    0.48
    Activations Density 1.044%

    No Known Activations