© 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. 7542
    Prev
    Next
    INDEX
    Explanations

    examples of representative samples or images

    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
    principalColumn
    -0.61
    BrowserModule
    -0.60
    انجليز
    -0.57
     BIBSYS
    -0.56
    voltaic
    -0.53
     mắn
    -0.53
    sidemargin
    -0.52
     matern
    -0.52
    servez
    -0.52
    ular
    -0.51
    POSITIVE LOGITS
     representative
    2.67
     Representative
    2.52
    Representative
    2.48
    representative
    2.48
     Representatives
    1.90
     representatives
    1.88
    Representatives
    1.63
     representante
    1.52
     REPRESENTATIVES
    1.44
     représentants
    1.43
    Activations Density 0.007%

    No Known Activations