© 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. 43683
    Prev
    Next
    INDEX
    Explanations

    do

    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
     do
    -1.02
    do
    -0.95
    Do
    -0.83
     Do
    -0.81
    RenderAtEndOf
    -0.68
     DO
    -0.64
    DO
    -0.62
    IGraphics
    -0.58
    SuccessListener
    -0.53
    istoitu
    -0.53
    POSITIVE LOGITS
     Shakspeare
    0.70
     ―――――
    0.68
     itſelf
    0.65
     ſeveral
    0.65
     Houſe
    0.64
     ་་
    0.63
     ♂
    0.62
     Monfieur
    0.62
     Mahomet
    0.60
     Majefty
    0.60
    Activations Density 0.050%

    No Known Activations