© 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. 5-CLT-HP
    7. 560
    Prev
    Next
    INDEX
    Explanations

    Locations

    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
    endregion
    -0.68
    SceneManagement
    -0.65
    EndInit
    -0.59
    //
    -0.57
    /*
    -0.53
    mok
    -0.50
    requireNonNull
    -0.48
    TryParse
    -0.48
    destroyAll
    -0.47
     geograf
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.63
    AsUp
    0.59
     Haitian
    0.58
     Bantu
    0.58
     الرياضيه
    0.57
    SharedDtor
    0.57
     Moscou
    0.55
    awtextra
    0.55
     MainAxisSize
    0.55
     Flemish
    0.54
    Activations Density 0.003%

    No Known Activations