© 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. 1-RES-MATRYOSHKA-DC
    7. 1409
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions

    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
    __':
    -0.70
    __":
    -0.59
     GBIF
    -0.59
    prnewswire
    -0.57
     уважением
    -0.57
    expandindo
    -0.56
    thenReturn
    -0.55
    Theorem
    -0.54
    AlterField
    -0.54
    FXML
    -0.52
    POSITIVE LOGITS
     describe
    3.55
     description
    3.50
     descriptions
    3.31
     describes
    3.17
     described
    3.13
     describing
    3.09
     Description
    2.95
     DESCR
    2.94
    description
    2.91
     Describe
    2.88
    Activations Density 0.169%

    No Known Activations