© 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. 3-RES-MATRYOSHKA-DC
    7. 3248
    Prev
    Next
    INDEX
    Explanations

    mentions of "cell lines" (usually within biological research contexts)

    oai_token-act-pair · gemini-2.0-flash
    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
     fenomeno
    -0.69
    reportWebVitals
    -0.69
    liesslich
    -0.68
     segnale
    -0.66
     aislados
    -0.65
    RTEE
    -0.65
    addContainerGap
    -0.64
     InputDecoration
    -0.64
     aisladas
    -0.64
     civilización
    -0.63
    POSITIVE LOGITS
     lines
    0.69
    ButterKnife
    0.57
    othelioma
    0.55
    Phas
    0.54
     LINES
    0.53
     pillow
    0.53
     Bridal
    0.53
     periodi
    0.50
     almohada
    0.50
     Lines
    0.49
    Activations Density 0.005%

    No Known Activations