© 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. 7631
    Prev
    Next
    INDEX
    Explanations

    passages about infants or very young babies

    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
    ñon
    -0.55
    wright
    -0.54
    matricula
    -0.51
     Wur
    -0.50
    ומות
    -0.50
     La
    -0.49
     Ola
    -0.49
    Vegeu
    -0.48
    ria
    -0.48
    printLine
    -0.48
    POSITIVE LOGITS
     baby
    3.20
    Baby
    3.00
     Baby
    2.98
    baby
    2.95
     BABY
    2.83
    BABY
    2.58
     bébé
    2.25
     babies
    2.23
    babies
    1.95
     Babies
    1.91
    Activations Density 0.018%

    No Known Activations