© 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. 9117
    Prev
    Next
    INDEX
    Explanations

    a

    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
    OfWeek
    -0.50
     Paglinawan
    -0.48
     spesielt
    -0.48
     trajets
    -0.47
    mstyle
    -0.47
     ragazze
    -0.46
    ьаж
    -0.46
    putnik
    -0.45
     aprobó
    -0.44
     clôture
    -0.43
    POSITIVE LOGITS
     result
    0.64
     MonoBehaviour
    0.64
    TagMode
    0.62
     Pingback
    0.60
     Lifeline
    0.60
    انگلیسی
    0.58
     consequence
    0.58
    Datuak
    0.58
    SequentialGroup
    0.57
     means
    0.57
    Activations Density 0.116%

    No Known Activations