© 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. 12-RES-MATRYOSHKA-DC
    7. 21089
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "ub" and similar variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Guthrie
    -1.00
     Manuela
    -0.81
     McCabe
    -0.72
     Samuels
    -0.72
     McGee
    -0.72
     Adela
    -0.71
    Архівовано
    -0.70
     Tilly
    -0.70
     Rutherford
    -0.69
     Jaffe
    -0.69
    POSITIVE LOGITS
    ub
    1.18
    Lub
    0.96
     Lub
    0.96
     UB
    0.96
     Gub
    0.96
     ub
    0.94
    UB
    0.92
    tub
    0.85
    ectoria
    0.81
    Bub
    0.81
    Activations Density 0.013%

    No Known Activations