© 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. 110
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     kaarangay
    -0.53
    eriks
    -0.52
     charters
    -0.52
    SharedCtor
    -0.51
     charges
    -0.50
     daggers
    -0.49
     knives
    -0.48
     Hanuman
    -0.48
    openhague
    -0.48
     Mø
    -0.47
    POSITIVE LOGITS
    PreferredItem
    0.57
    MLLoader
    0.53
     Paglinawan
    0.49
    CLC
    0.49
    WriteTagHelper
    0.48
    󠁣
    0.46
    ytet
    0.45
    tagHelperRunner
    0.45
     Allociné
    0.45
     старости
    0.45
    Activations Density 0.019%

    No Known Activations