© 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. 6061
    Prev
    Next
    INDEX
    Explanations

    references to listening or hearing experiences and stories

    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
    CrossRef
    -0.97
    idavit
    -0.79
     ​​
    -0.79
     PHILL
    -0.71
    DotNetBar
    -0.69
    ErrUnexpectedEOF
    -0.69
     Sub
    -0.68
    namental
    -0.67
     Duf
    -0.67
     transfieras
    -0.67
    POSITIVE LOGITS
    Heard
    1.28
     hears
    1.27
     Hearn
    1.27
     Heard
    1.27
     hear
    1.20
     heard
    1.17
     HEAR
    1.17
     Hear
    1.14
    hear
    1.09
    Hear
    1.08
    Activations Density 0.043%

    No Known Activations