© 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. 97213
    Prev
    Next
    INDEX
    Explanations

    important

    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
    isDebugEnabled
    -0.63
     to
    -0.62
    jecture
    -0.52
    Vale
    -0.52
     essentielles
    -0.51
    beto
    -0.50
     Vale
    -0.50
    fromCharCode
    -0.49
     est
    -0.49
     essentiel
    -0.48
    POSITIVE LOGITS
    تقاوى
    1.02
     ſmall
    0.98
     faſt
    0.95
     houſe
    0.90
    ſelves
    0.89
    الحياه
    0.88
    tagHelperRunner
    0.88
     purpoſe
    0.85
     ſta
    0.84
     ſte
    0.84
    Activations Density 0.178%

    No Known Activations