© 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. 2325
    Prev
    Next
    INDEX
    Explanations

    technical 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
    .
    -0.42
    iem
    -0.42
     than
    -0.40
    q
    -0.40
    wc
    -0.39
     civil
    -0.39
     
    -0.39
     from
    -0.39
     in
    -0.38
    [^
    -0.37
    POSITIVE LOGITS
     يتيمه
    1.12
    parsedMessage
    0.98
     дописавши
    0.97
    MLLoader
    0.97
    
    0.93
    NewUrlParser
    0.92
    tagext
    0.91
    DockStyle
    0.90
    IVEREF
    0.90
    ########.
    0.89
    Activations Density 0.004%

    No Known Activations