© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14830
    Prev
    Next
    INDEX
    Explanations

    from

    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
     berta
    -0.50
    e
    -0.48
    re
    -0.46
     e
    -0.44
    Genial
    -0.44
    o
    -0.43
    ModelAttribute
    -0.42
     gen
    -0.42
    y
    -0.41
      
    -0.38
    POSITIVE LOGITS
     تضيفلها
    1.05
    )_/¯
    0.85
     myſelf
    0.85
     fubject
    0.83
    Демографія
    0.81
     Efq
    0.79
     purpoſe
    0.78
    NameInMap
    0.77
    twimg
    0.77
    ſelves
    0.76
    Activations Density 0.001%

    No Known Activations