© 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. 2273
    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
    NameInMap
    -0.83
     تضيفلها
    -0.82
     дописавши
    -0.76
    ьаж
    -0.75
     oprot
    -0.73
    
    -0.71
    GEBURTS
    -0.71
    GOTREF
    -0.70
    +#+#
    -0.69
     debout
    -0.68
    POSITIVE LOGITS
     comp
    0.56
     measuring
    0.54
     finding
    0.52
    comp
    0.46
     simple
    0.45
     Par
    0.45
     arqu
    0.44
     quer
    0.44
     She
    0.43
    gets
    0.42
    Activations Density 0.003%

    No Known Activations