© 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. 2-RES-MATRYOSHKA-DC
    7. 3257
    Prev
    Next
    INDEX
    Explanations

    references to thermal effects or heat-related phenomena

    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
     Mercu
    -0.77
     JST
    -0.70
    Cool
    -0.69
     doInBackground
    -0.68
     Cool
    -0.67
    TURE
    -0.67
    :✨
    -0.67
     PropTypes
    -0.66
    cool
    -0.65
     ThemeData
    -0.65
    POSITIVE LOGITS
     thermal
    2.72
     Thermal
    2.39
    Thermal
    2.39
    thermal
    2.23
     thermally
    1.52
     térmica
    1.37
     thermique
    1.34
     térm
    1.31
     térmico
    1.18
     THER
    0.96
    Activations Density 0.010%

    No Known Activations