© 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. 3286
    Prev
    Next
    INDEX
    Explanations

    mentions of filaments and twist ties

    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
    awtextra
    -0.90
    Platz
    -0.66
    olstein
    -0.65
    Blit
    -0.65
     Bins
    -0.65
    Сту
    -0.64
    FileChooser
    -0.63
     ناد
    -0.63
     Robbins
    -0.62
    crollView
    -0.62
    POSITIVE LOGITS
     filaments
    1.18
     filament
    1.12
     strands
    1.11
     Filament
    1.05
    fila
    0.98
     ribbon
    0.96
     tangled
    0.96
     strand
    0.96
     twisted
    0.94
    twist
    0.94
    Activations Density 0.500%

    No Known Activations