© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 392
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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
     للاسماء
    -0.69
    DotNetBar
    -0.65
    BindView
    -0.61
    classnames
    -0.59
     kasarigan
    -0.59
    Revenir
    -0.55
     Quadrant
    -0.54
     disponibilités
    -0.54
    contentLoaded
    -0.54
     Cred
    -0.54
    POSITIVE LOGITS
     насељу
    0.55
    inheritDoc
    0.50
     that
    0.50
     immigration
    0.49
     building
    0.48
    htar
    0.47
    cshtml
    0.46
     foreign
    0.46
     competition
    0.46
    SdkVersion
    0.46
    Activations Density 0.001%

    No Known Activations