© 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. 1-RES-MATRYOSHKA-DC
    7. 1559
    Prev
    Next
    INDEX
    Explanations

    references to water or aqueous solutions

    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
    CppCodeGen
    -0.59
     كومونز
    -0.58
     Италијани
    -0.58
     noqa
    -0.55
     oprot
    -0.55
     Knit
    -0.54
     Astrophysics
    -0.54
     INSEE
    -0.52
    Knit
    -0.52
    клопе
    -0.51
    POSITIVE LOGITS
     water
    4.50
     Water
    4.13
    Water
    4.06
    water
    3.97
     WATER
    3.78
    WATER
    3.59
     waters
    3.02
    水
    2.80
     Wasser
    2.73
     agua
    2.70
    Activations Density 0.511%

    No Known Activations