© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    references to types of edible grains used in food, such as corn, wheat, and soy

    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
    Negative Logits
    IntoConstraints
    -0.76
    Rptr
    -0.66
     CURIAM
    -0.63
    Obrázky
    -0.60
    omotor
    -0.57
    зулта
    -0.57
     дописавши
    -0.56
     Maastricht
    -0.56
    TargetException
    -0.56
    apeno
    -0.56
    POSITIVE LOGITS
     grain
    2.91
     Grain
    2.77
     grains
    2.58
    Grain
    2.53
    grain
    2.50
     Grains
    2.42
    grains
    2.16
     rice
    2.00
     wheat
    1.87
     Rice
    1.84
    Activations Density 0.083%

    No Known Activations