© 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. 90636
    Prev
    Next
    INDEX
    Explanations

    dan

    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
    dan
    -0.94
     Din
    -0.63
    Din
    -0.63
    din
    -0.56
    DAN
    -0.55
    ează
    -0.54
    iastes
    -0.52
    ход
    -0.51
    DllImport
    -0.50
     dodged
    -0.50
    POSITIVE LOGITS
    GTCX
    0.62
    ējās
    0.62
     المعيارى
    0.61
    ValueStyle
    0.60
     typelib
    0.59
    
    0.59
    abestanden
    0.58
    LoginComponent
    0.58
     الحره
    0.57
     utafitiHapana
    0.57
    Activations Density 0.056%

    No Known Activations