© 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. 2656
    Prev
    Next
    INDEX
    Explanations

    activity related to the estrogen receptor (ER) pathway

    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
    Portale
    -0.63
     Keller
    -0.63
     /\.(
    -0.59
    hiel
    -0.58
     Pes
    -0.57
     Curi
    -0.57
     Waters
    -0.57
     Alonso
    -0.56
    KeyEvent
    -0.54
    AndroidJUnit
    -0.54
    POSITIVE LOGITS
     ER
    2.45
     er
    2.41
     Er
    2.20
    Er
    2.09
    ER
    1.57
     Eras
    1.34
     Erm
    1.20
     Erb
    1.17
     ERS
    1.13
     ERA
    1.09
    Activations Density 0.048%

    No Known Activations