© 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. 0-CLT-HP
    7. 1354
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     importance
    -0.78
     Importance
    -0.64
     mediator
    -0.62
     molecules
    -0.61
    Importance
    -0.59
    importance
    -0.59
     mediate
    -0.58
     pages
    -0.56
     importancia
    -0.56
    밌
    -0.55
    POSITIVE LOGITS
    Hochspringen
    0.75
    वरी
    0.54
     intptr
    0.54
    стр
    0.54
    ępu
    0.54
     BrowserModule
    0.54
    ImageContext
    0.53
     recognising
    0.52
     Assy
    0.50
     Mali
    0.50
    Activations Density 1.090%

    No Known Activations