© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical notation and limits

    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
     nahilalakip
    -0.83
     Efq
    -0.82
     crdi
    -0.70
     disambiguazione
    -0.68
     Shakspeare
    -0.65
     CreateTagHelper
    -0.65
    principalColumn
    -0.63
    PARATUS
    -0.63
     isComment
    -0.63
    casio
    -0.62
    POSITIVE LOGITS
    انيف
    0.57
    houd
    0.52
     ceb
    0.49
     mim
    0.44
     Cesar
    0.42
     هيا
    0.42
    defin
    0.42
     dene
    0.41
     Cohn
    0.41
    do
    0.41
    Activations Density 0.480%

    No Known Activations