© 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. 22-RES-MATRYOSHKA-DC
    7. 3291
    Prev
    Next
    INDEX
    Explanations

    words related to audio, music and sound

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     son
    -0.53
     Abp
    -0.50
    (;;)
    -0.49
    autoIncrement
    -0.48
     wachten
    -0.48
     connexe
    -0.48
     rând
    -0.47
    bestimmungen
    -0.46
    طني
    -0.46
    oraz
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.70
    ագրություններ
    0.65
    bite
    0.64
    tracks
    0.62
    capes
    0.59
    Vidite
    0.57
    bites
    0.57
    imageio
    0.56
    afone
    0.56
    lessly
    0.55
    Activations Density 0.100%

    No Known Activations