© 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. 2586
    Prev
    Next
    INDEX
    Explanations

    instances of singing or singing-related actions

    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
    LookAnd
    -0.85
     gear
    -0.69
    Datuak
    -0.67
    AsUp
    -0.66
    GEAR
    -0.66
     وتسجيلات
    -0.66
     للمعارف
    -0.66
    ثيق
    -0.66
     ActionListener
    -0.65
    piti
    -0.65
    POSITIVE LOGITS
     sing
    2.34
     singing
    2.31
     sings
    2.31
     sang
    2.16
     Singing
    1.95
    singing
    1.95
     sung
    1.92
    Singing
    1.91
     Sing
    1.91
    Sing
    1.90
    Activations Density 0.069%

    No Known Activations