© 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. 17725
    Prev
    Next
    INDEX
    Explanations

    terms related to ear anatomy and devices associated with hearing

    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
     Hess
    -0.78
    lccn
    -0.71
     Barbar
    -0.67
     Robins
    -0.66
     Fußballspieler
    -0.65
    rictions
    -0.65
     Spectra
    -0.62
    λλ
    -0.62
     ​​
    -0.61
     Ricci
    -0.61
    POSITIVE LOGITS
     Ear
    1.64
     ear
    1.58
    Ear
    1.47
     ears
    1.45
     EAR
    1.39
     Ears
    1.34
     Earle
    1.27
     oreille
    1.18
     oreilles
    1.16
     Ohr
    1.02
    Activations Density 0.015%

    No Known Activations