© 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. 97123
    Prev
    Next
    INDEX
    Explanations

    subtle

    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
     II
    -0.82
    II
    -0.68
    invisible
    -0.67
     sur
    -0.60
     weed
    -0.56
     уда
    -0.52
    übung
    -0.51
     milliers
    -0.51
     sa
    -0.50
    vic
    -0.50
    POSITIVE LOGITS
     itſelf
    0.82
     myſelf
    0.77
     linkovi
    0.77
     дописавши
    0.76
    Rohy
    0.74
     للاسماء
    0.74
     ―――――
    0.73
    
    0.73
    ſelves
    0.72
    ſelf
    0.72
    Activations Density 0.096%

    No Known Activations