© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    specific mentions of flange components or highly activated flange-related tokens

    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
     CreateTagHelper
    -0.59
    OrBuilder
    -0.54
     sappi
    -0.54
    AndroidJUnit
    -0.53
    δες
    -0.53
     frattempo
    -0.52
    Nationalité
    -0.51
    ngdoc
    -0.50
     Toc
    -0.48
    SPATH
    -0.48
    POSITIVE LOGITS
    ρά
    2.91
    ρα
    2.89
    ΡΑ
    1.30
    ρασ
    1.15
    ρας
    1.10
    setupUi
    0.91
     flange
    0.90
     flanges
    0.81
    ρες
    0.77
    DockStyle
    0.70
    Activations Density 0.001%

    No Known Activations