© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20626
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical operations and variables

    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
    Negative Logits
    enance
    -0.75
    ignty
    -0.71
    Benson
    -0.69
    yng
    -0.68
     Nong
    -0.67
    ebly
    -0.66
    ofür
    -0.66
     ResNet
    -0.66
    lessly
    -0.66
    urrection
    -0.65
    POSITIVE LOGITS
    Xr
    1.04
     AssemblyCulture
    0.82
    ValueStyle
    0.79
    𝑟
    0.78
    原始内容存档于
    0.77
     Cfr
    0.76
    ณะ
    0.75
     Rohr
    0.75
     Corso
    0.75
     Cider
    0.74
    Activations Density 0.087%

    No Known Activations