© 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. 4-CLT-HP
    7. 2907
    Prev
    Next
    INDEX
    Explanations

    snippets of larger documents

    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
     itſelf
    -0.91
    出版年
    -0.77
     himſelf
    -0.75
     myſelf
    -0.69
     themſelves
    -0.65
    hdashline
    -0.63
     iſt
    -0.59
     ſeveral
    -0.59
    avadoc
    -0.59
     Efq
    -0.59
    POSITIVE LOGITS
    Искәрмәләр
    0.57
    Either
    0.56
    ContentAsync
    0.55
    SharedDtor
    0.52
     Either
    0.52
    ípio
    0.52
    Portale
    0.52
     either
    0.51
    EREF
    0.51
     invece
    0.50
    Activations Density 0.005%

    No Known Activations