© 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. 7400
    Prev
    Next
    INDEX
    Explanations

    references to figures, specifically figure numbers and labels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fraî
    -0.61
     artificiales
    -0.59
    Clik
    -0.58
     Вікі
    -0.57
     mauvaises
    -0.57
     scolaires
    -0.55
     femeninos
    -0.54
     agrícolas
    -0.54
     colectivos
    -0.54
     solides
    -0.53
    POSITIVE LOGITS
    Искәрмәләр
    0.84
    ⓧ
    0.71
     henvisninger
    0.68
     كومونز
    0.68
    DispatchToProps
    0.67
     Мексичка
    0.65
     disambiguazione
    0.65
    таратура
    0.65
     invokingState
    0.64
    XmlType
    0.62
    Activations Density 0.034%

    No Known Activations