© 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. 97175
    Prev
    Next
    INDEX
    Explanations

    ISBN

    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
    ISBN
    -0.85
    Witam
    -0.66
     getRule
    -0.54
    ruptedException
    -0.53
    stateMutability
    -0.48
    tagext
    -0.48
    Researchers
    -0.47
    tibus
    -0.47
     lecturers
    -0.46
    utnant
    -0.45
    POSITIVE LOGITS
     propOrder
    0.73
    s
    0.68
     inférieure
    0.62
    تقاوى
    0.61
     Chwiliwch
    0.60
    شهاد
    0.59
     stället
    0.57
    ValueStyle
    0.57
    sor
    0.56
     définiti
    0.56
    Activations Density 1.608%

    No Known Activations