© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 157
    Prev
    Next
    INDEX
    Explanations

    words relating to chemical compounds

    oai_token-act-pair · gemini-2.0-flash
    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
     orthodon
    -0.72
     Numerology
    -0.71
     Kines
    -0.68
    Hozzáférés
    -0.68
     mẽ
    -0.68
     Teles
    -0.67
    othelioma
    -0.66
     *>(
    -0.65
     Knitting
    -0.65
    complishments
    -0.65
    POSITIVE LOGITS
     substance
    0.71
     substances
    0.70
     salts
    0.69
    anyag
    0.68
    ingredients
    0.66
     ingredients
    0.65
     materials
    0.65
     compounds
    0.64
    Ingredient
    0.63
     anyag
    0.63
    Activations Density 4.331%

    No Known Activations