© 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. 18749
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a promise or commitment

    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
     Efq
    -1.06
     Theſe
    -0.95
     myſelf
    -0.94
     ſeveral
    -0.94
     itſelf
    -0.92
     ſhall
    -0.88
     Мексичка
    -0.88
     Houſe
    -0.88
     fhall
    -0.87
     Majefty
    -0.87
    POSITIVE LOGITS
     trekken
    0.59
     For
    0.59
     plastiques
    0.56
     By
    0.56
     fram
    0.55
     Porque
    0.55
    raltar
    0.54
    For
    0.52
     since
    0.51
     perchè
    0.51
    Activations Density 0.023%

    No Known Activations