© 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. 2164
    Prev
    Next
    INDEX
    Explanations

    names

    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
     CreateTagHelper
    -0.71
     Monfieur
    -0.54
     himſelf
    -0.52
     poffe
    -0.51
     quæ
    -0.51
     SANTA
    -0.51
     uſed
    -0.51
     BoxDecoration
    -0.51
     myſelf
    -0.51
    dAtA
    -0.49
    POSITIVE LOGITS
    ruptedException
    0.60
    MLLoader
    0.59
     Bridge
    0.52
     очередь
    0.49
     Bech
    0.47
    ToRefresh
    0.47
    EnableWeb
    0.47
    Архівовано
    0.46
    weile
    0.45
     Fehl
    0.45
    Activations Density 0.164%

    No Known Activations