© 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. 10431
    Prev
    Next
    INDEX
    Explanations

    numerical values and dimensions related to scientific measurements

    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
    गत
    -0.51
    mase
    -0.51
    matur
    -0.50
    ✭✭
    -0.49
    <b>
    -0.48
    seys
    -0.47
    >|
    -0.45
    一步
    -0.45
     Step
    -0.45
    εια
    -0.45
    POSITIVE LOGITS
    webElementXpaths
    0.80
    EndProject
    0.66
    posedge
    0.65
     fubject
    0.65
     myſelf
    0.65
     pleaſure
    0.64
    símbolo
    0.63
    లాలు
    0.62
    Билгалдахарш
    0.62
     itſelf
    0.62
    Activations Density 0.036%

    No Known Activations