© 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. 4-CLT-HP
    7. 4719
    Prev
    Next
    INDEX
    Explanations

    far

    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
    GOTREF
    -0.58
     Préférences
    -0.55
     emulsi
    -0.53
    Biografi
    -0.52
     gangen
    -0.51
     EnglishChoose
    -0.50
     useAppContext
    -0.49
     thiệu
    -0.49
    ⓧ
    -0.49
     feroit
    -0.48
    POSITIVE LOGITS
    
    0.63
     beyond
    0.60
     outweigh
    0.57
    beyond
    0.56
     longer
    0.56
    Longer
    0.56
     سكانية
    0.54
     wider
    0.54
    wider
    0.52
     greater
    0.52
    Activations Density 0.003%

    No Known Activations