© 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. 2-RES-MATRYOSHKA-DC
    7. 2698
    Prev
    Next
    INDEX
    Explanations

    the word "ear" and related terms associated with hearing devices

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abitanti
    -0.66
    TestBed
    -0.65
    Šaltiniai
    -0.63
     oprot
    -0.61
    — 
    -0.60
     Medford
    -0.59
    Ҭ
    -0.59
    sounding
    -0.58
    GFX
    -0.58
    scut
    -0.58
    POSITIVE LOGITS
     ear
    3.66
     Ear
    3.33
    Ear
    3.11
    ear
    2.80
     EAR
    2.53
     ears
    2.28
    EAR
    2.11
     Ears
    1.97
    ears
    1.52
     oreille
    1.50
    Activations Density 0.008%

    No Known Activations