© 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. 0-RES-MATRYOSHKA-DC
    7. 10537
    Prev
    Next
    INDEX
    Explanations

    layers of photosensitive compounds that respond to specific wavelengths of light

    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
    webElement
    -0.92
    LookAnd
    -0.76
     Roskov
    -0.76
    findpost
    -0.74
    ]='\
    -0.65
    kuuta
    -0.65
    scriptcase
    -0.65
    urtz
    -0.63
    Geplaatst
    -0.60
    SpringBootTest
    -0.60
    POSITIVE LOGITS
    licative
    0.91
    etary
    0.65
    alog
    0.64
    kop
    0.64
     curd
    0.63
    cljs
    0.63
     Beckman
    0.62
    alogical
    0.62
    pard
    0.61
    ango
    0.61
    Activations Density 0.064%

    No Known Activations