© 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. 38396
    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
     mag
    -0.75
     na
    -0.67
     du
    -0.67
    ification
    -0.61
     Mag
    -0.58
    lag
    -0.54
     py
    -0.51
     upon
    -0.49
     Du
    -0.48
    ken
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.73
     houſe
    0.72
     fubject
    0.69
     Houſe
    0.69
     Monfieur
    0.69
     Anſ
    0.68
    şiv
    0.68
    SBATCH
    0.68
     Diſ
    0.68
     preſent
    0.67
    Activations Density 0.355%

    No Known Activations