© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11683
    Prev
    Next
    INDEX
    Explanations

    breath

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breathing
    -0.62
     breath
    -0.60
     breathe
    -0.59
    Breathing
    -0.57
     breathed
    -0.54
     Breathing
    -0.52
    TagMode
    -0.49
     respiración
    -0.49
     Breathe
    -0.49
     distracted
    -0.49
    POSITIVE LOGITS
    ########.
    0.69
    SizeF
    0.68
    ImageContext
    0.65
    исленность
    0.61
     betweenstory
    0.60
     utafitiHapana
    0.59
    contentLoaded
    0.59
    ViewFeatures
    0.58
    itudinal
    0.57
    MockBean
    0.56
    Activations Density 0.007%

    No Known Activations