© 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. 0-CLT-HP
    7. 90902
    Prev
    Next
    INDEX
    Explanations

    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
     ſeveral
    -0.71
     writing
    -0.66
     Writing
    -0.63
     Jefus
    -0.63
     faſt
    -0.58
    Writing
    -0.57
    lamy
    -0.54
     laſt
    -0.54
     Longueur
    -0.54
     againſt
    -0.54
    POSITIVE LOGITS
    twimg
    0.62
     team
    0.57
    apimachinery
    0.52
    backers
    0.51
    levance
    0.49
    eryllium
    0.49
     crew
    0.49
     насељу
    0.48
     AssemblyVersion
    0.47
    raszamy
    0.47
    Activations Density 0.039%

    No Known Activations