© 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. 5-CLT-HP
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    Magi

    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
    ROIT
    -0.58
     Schal
    -0.54
    Ѓ
    -0.48
    lė
    -0.46
     começo
    -0.46
    dė
    -0.46
    ftagPool
    -0.46
     intérieure
    -0.46
    ather
    -0.45
     pescoço
    -0.45
    POSITIVE LOGITS
    oredCriteria
    0.61
    TintMode
    0.59
    ItemBackground
    0.55
    MemoryWarning
    0.50
    $")
    0.50
    EndInit
    0.48
    [])
    0.47
     onOptions
    0.46
    )"),
    0.46
    getDescriptor
    0.46
    Activations Density 0.002%

    No Known Activations