© 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. 7639
    Prev
    Next
    INDEX
    Explanations

    examples of specific quantities or subsets, such as words indicating a certain number or proportion

    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
     therefore
    -0.59
     however
    -0.57
    therefore
    -0.54
    thus
    -0.53
     one
    -0.52
    TestFixture
    -0.51
     so
    -0.50
    however
    -0.50
    enskap
    -0.49
    isn
    -0.48
    POSITIVE LOGITS
     للمعارف
    1.16
     Many
    0.88
     Alguns
    0.85
     Some
    0.81
     Certains
    0.81
     Others
    0.79
     Another
    0.79
    Others
    0.78
     Other
    0.77
     Certain
    0.77
    Activations Density 0.418%

    No Known Activations