© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11400
    Prev
    Next
    INDEX
    Explanations

    go

    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
     Mih
    -0.52
    chik
    -0.50
     sàng
    -0.49
     zab
    -0.49
    죠
    -0.47
     dispositifs
    -0.47
     Goes
    -0.47
    ÁN
    -0.46
    éviter
    -0.46
     chaînes
    -0.46
    POSITIVE LOGITS
     الحره
    0.67
    AddHtmlAttribute
    0.66
     Normdatei
    0.66
    OGND
    0.65
    GetEnumerator
    0.65
    IBOutlet
    0.62
    dotenv
    0.62
    CloseOperation
    0.61
    ########.
    0.59
     كومونز
    0.59
    Activations Density 0.002%

    No Known Activations