© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43577
    Prev
    Next
    INDEX
    Explanations

    breathing

    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
    -1.00
     blink
    -0.83
    ConstraintMaker
    -0.77
     wind
    -0.77
    breathing
    -0.75
    Breathing
    -0.74
     Breathing
    -0.72
    RTDA
    -0.70
    +:+
    -0.67
     breathe
    -0.66
    POSITIVE LOGITS
    ers
    0.65
    word
    0.60
    less
    0.59
    words
    0.58
    wave
    0.54
    les
    0.53
    iness
    0.52
    lines
    0.52
    plot
    0.52
    ride
    0.52
    Activations Density 0.214%

    No Known Activations