© 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. 2818
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ?
    -0.63
     be
    -0.59
     at
    -0.44
     take
    -0.43
     get
    -0.42
    ？
    -0.41
     most
    -0.41
     not
    -0.40
     tell
    -0.40
     remind
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    1.00
    
    0.94
     NSCoder
    0.86
     myſelf
    0.84
    Personensuche
    0.84
     Италијани
    0.83
     resourceCulture
    0.82
    ArrowToggle
    0.81
     Theſe
    0.80
     oprot
    0.79
    Activations Density 0.004%

    No Known Activations