© 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. 23467
    Prev
    Next
    INDEX
    Explanations

    terms related to the throat and esophagus

    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
    MessageTagHelper
    -0.74
     fecund
    -0.70
    kabau
    -0.68
     feldspar
    -0.67
    NOPQRST
    -0.67
     Astor
    -0.66
    TestFixture
    -0.66
     newArr
    -0.66
     Igu
    -0.65
     विश्वसनीयता
    -0.64
    POSITIVE LOGITS
     throat
    1.38
    ophageal
    1.23
     Throat
    1.20
     throats
    1.08
    ophagus
    1.05
     esophageal
    1.02
    throat
    1.02
    aryngeal
    0.98
     esophagus
    0.90
    咽
    0.89
    Activations Density 0.018%

    No Known Activations