© 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. 1-CLT-HP
    7. 13544
    Prev
    Next
    INDEX
    Explanations

    with

    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
     a
    -0.50
    :
    -0.50
    лив
    -0.48
    дь
    -0.47
    :[]
    -0.43
     p
    -0.42
     StatelessWidget
    -0.42
    <bos>
    -0.42
    ↵
    -0.41
     
    -0.41
    POSITIVE LOGITS
     pleaſure
    0.99
     Jefus
    0.94
     itſelf
    0.91
     Anſ
    0.88
     myſelf
    0.87
    ſelf
    0.85
     themſelves
    0.84
     Chriftian
    0.83
     Monfieur
    0.82
     purpoſe
    0.80
    Activations Density 0.007%

    No Known Activations