© 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. 6-RES-MATRYOSHKA-DC
    7. 1434
    Prev
    Next
    INDEX
    Explanations

    terms related to ice, snow, and freezing, including scientific and common usages

    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
    Negative Logits
     propOrder
    -0.88
    #+#
    -0.86
    nextProps
    -0.86
     AssemblyCulture
    -0.85
    SequentialGroup
    -0.78
    verwijspagina
    -0.77
    énario
    -0.77
     فريبيس
    -0.75
    Personendaten
    -0.74
    ViewFeatures
    -0.73
    POSITIVE LOGITS
     ice
    1.94
     Ice
    1.74
     freeze
    1.73
     frozen
    1.68
    Ice
    1.63
     freezing
    1.61
     froze
    1.55
     Frozen
    1.55
     Freeze
    1.54
     freezer
    1.52
    Activations Density 0.531%

    No Known Activations