© 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. 2-RES-MATRYOSHKA-DC
    7. 2456
    Prev
    Next
    INDEX
    Explanations

    the similarity between different models or datasets

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    下载附件
    -0.59
     Reproduce
    -0.58
    msgTypes
    -0.56
    overrightarrow
    -0.56
    WebElementEntity
    -0.55
     margiela
    -0.55
    findpost
    -0.54
    لاثة
    -0.54
    mapsto
    -0.52
    dymyr
    -0.52
    POSITIVE LOGITS
    sim
    1.77
     ∼
    0.85
    sime
    0.84
    SIM
    0.82
    ∼
    0.74
     sim
    0.71
     Sim
    0.70
    Sim
    0.69
    sima
    0.68
     SIM
    0.64
    Activations Density 0.013%

    No Known Activations