© 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. 0-CLT-HP
    4. 1454
    Prev
    Next
    INDEX
    Explanations

    burnReason: Predominance of the word in MAX_ACTIVATING_TOKENSburn

    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
     sleep
    -1.35
     burn
    -1.00
     bed
    -0.92
     Sleep
    -0.86
    Besides
    -0.84
    sleep
    -0.79
    besides
    -0.76
     besides
    -0.75
     Besides
    -0.73
    Sleep
    -0.68
    POSITIVE LOGITS
    ients
    0.60
    @[+][
    0.58
    ngrx
    0.57
    :✨
    0.56
    Atsauces
    0.55
    lessness
    0.54
     Walkover
    0.53
    kits
    0.53
    dressing
    0.52
    intios
    0.52
    Activations Density 0.013%

    No Known Activations