© 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. 6306
    Prev
    Next
    INDEX
    Explanations

    instances of polite requests or forms of "please."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ation
    -0.77
    ATION
    -0.71
     Kopp
    -0.67
    ations
    -0.64
    낼
    -0.64
     Erik
    -0.64
    untergang
    -0.61
    autorité
    -0.60
     Haan
    -0.60
    GMENT
    -0.60
    POSITIVE LOGITS
     please
    1.24
     Please
    1.20
    Please
    1.18
     PLEASE
    1.15
    please
    1.13
    PLEASE
    1.13
     Kindly
    1.11
    Pls
    1.03
     Bitte
    1.01
     Pls
    1.00
    Activations Density 0.018%

    No Known Activations