© 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. 15032
    Prev
    Next
    INDEX
    Explanations

    numerical values or references, particularly related to statistics or data points

    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
    ushin
    -0.82
    twimg
    -0.71
    帖最后由
    -0.71
     setContent
    -0.69
     depth
    -0.68
    Datuak
    -0.68
     Depth
    -0.67
     Bü
    -0.66
    EClass
    -0.66
    ادث
    -0.66
    POSITIVE LOGITS
    ArgsConstructor
    0.74
     Lear
    0.71
     Marr
    0.69
     Vega
    0.69
    cetin
    0.68
     Martel
    0.66
     Warne
    0.65
    szön
    0.64
     Martine
    0.64
    ậc
    0.64
    Activations Density 0.378%

    No Known Activations