© 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. 31847
    Prev
    Next
    INDEX
    Explanations

    terms related to audio and sound

    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
    antMatchers
    -0.97
    NameInMap
    -0.89
    soort
    -0.78
    MessageOf
    -0.78
    Yess
    -0.76
    bcrypt
    -0.74
    IndentedString
    -0.73
    ので
    -0.72
     Verge
    -0.72
     Rass
    -0.71
    POSITIVE LOGITS
     Audio
    1.13
     audio
    1.11
     AUDIO
    1.11
    Audio
    0.98
    audio
    0.92
    AUDIO
    0.88
    phile
    0.83
     Aud
    0.71
     aud
    0.70
     Fudge
    0.70
    Activations Density 0.011%

    No Known Activations