© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5012
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of heat or warmth

    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
    Not in Any Lists

    No Comments

    Negative Logits
     térmica
    -0.66
     vapeur
    -0.63
    Электро
    -0.60
     vantaggio
    -0.59
     piele
    -0.58
     Hitze
    -0.58
     crainte
    -0.58
    cairo
    -0.57
     spécialisé
    -0.57
    ệc
    -0.57
    POSITIVE LOGITS
     warm
    3.19
    warm
    3.00
    Warm
    2.92
     Warm
    2.92
     WARM
    2.70
    WARM
    2.52
     warms
    2.34
     warmer
    2.31
     warmest
    2.19
     warmed
    2.17
    Activations Density 0.007%

    No Known Activations