© 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. 0-CLT-HP
    7. 41860
    Prev
    Next
    INDEX
    Explanations

    licenses and 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
     estekak
    -0.48
    église
    -0.43
    Église
    -0.39
     lenker
    -0.39
    Putting
    -0.38
     putting
    -0.38
     ب
    -0.37
     put
    -0.36
     leder
    -0.35
     stok
    -0.35
    POSITIVE LOGITS
     itſelf
    0.83
     Reſ
    0.81
     Monfieur
    0.81
     Diſ
    0.80
    
    0.78
    ertia
    0.76
     pleaſure
    0.76
     Anſ
    0.74
     Conſ
    0.73
    BibitemShut
    0.72
    Activations Density 0.062%

    No Known Activations