© 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. 0-CLT-HP
    7. 95064
    Prev
    Next
    INDEX
    Explanations

    re

    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
    stdc
    -0.51
     package
    -0.48
     all
    -0.46
     todos
    -0.45
     fait
    -0.45
     "
    -0.44
     պ
    -0.43
     p
    -0.43
     la
    -0.42
     form
    -0.42
    POSITIVE LOGITS
    IndentedString
    0.87
     Monfieur
    0.86
    Tikang
    0.84
     greateſt
    0.83
    InjectAttribute
    0.80
     ſche
    0.78
     ſever
    0.78
     leaſt
    0.78
     InputDecoration
    0.77
     kasarigan
    0.77
    Activations Density 0.285%

    No Known Activations