© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 65
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and processes related to metal extraction and treatment

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     ainfi
    -0.63
     tiegħ
    -0.60
     deſſen
    -0.59
     témoig
    -0.59
     unſer
    -0.59
     Geiſt
    -0.59
     erſt
    -0.58
    horloge
    -0.57
     sienta
    -0.57
     increí
    -0.56
    POSITIVE LOGITS
     water
    0.53
    expandindo
    0.45
     mixture
    0.43
     ProductService
    0.42
     Water
    0.41
     layer
    0.39
     liquid
    0.39
    shadowOpacity
    0.39
    vegetable
    0.38
     layers
    0.37
    Activations Density 10.394%

    No Known Activations