© 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. 10671
    Prev
    Next
    INDEX
    Explanations

    actions involving whispering or soft spoken communication

    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
     مرئيه
    -0.68
     surla
    -0.59
     GLC
    -0.57
     fireworks
    -0.57
     genu
    -0.54
    Lydia
    -0.54
    Faz
    -0.53
    epik
    -0.53
    盲
    -0.53
    {#
    -0.52
    POSITIVE LOGITS
     whispered
    0.97
     whisper
    0.90
     whispers
    0.83
    whisper
    0.82
     Whisper
    0.81
    قایناق‌لار
    0.81
     murmured
    0.77
     whispering
    0.77
     personalizadas
    0.75
    Whisper
    0.75
    Activations Density 0.004%

    No Known Activations