© 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. 5-CLT-HP
    7. 871
    Prev
    Next
    INDEX
    Explanations

    Start of formal documents

    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
     otomatig
    -0.74
    (!__
    -0.71
     <<<<<<<<<<<<<<
    -0.70
    createCanvas
    -0.67
    sidemargin
    -0.65
    MessageOf
    -0.65
     kasarigan
    -0.61
    NSNotification
    -0.60
    adpleegd
    -0.58
    //});
    -0.57
    POSITIVE LOGITS
    Personendaten
    0.57
    🧵
    0.52
     ReSharper
    0.50
    encio
    0.49
     autorytatywna
    0.49
    гда
    0.49
     Dedicated
    0.48
    MENAFN
    0.48
     cern
    0.47
     unum
    0.46
    Activations Density 0.195%

    No Known Activations