© 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. 0-CLT-HP
    7. 92755
    Prev
    Next
    INDEX
    Explanations

    technical descriptors and equations

    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
     Efq
    -1.06
     themſelves
    -1.03
     Theſe
    -1.03
     Jefus
    -1.02
     Houſe
    -1.02
     Monfieur
    -1.02
     houſe
    -1.00
     itſelf
    -0.99
     ſeveral
    -0.99
     ſtate
    -0.97
    POSITIVE LOGITS
    ical
    0.65
    ness
    0.64
    c
    0.60
    ary
    0.59
    n
    0.59
     Z
    0.58
    ation
    0.58
     par
    0.57
    son
    0.57
    burg
    0.57
    Activations Density 0.096%

    No Known Activations