© 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. 1-CLT-HP
    7. 759
    Prev
    Next
    INDEX
    Explanations

    journalism

    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
     culturelles
    -0.64
     appartements
    -0.58
     partag
    -0.57
    httphttps
    -0.57
     énergé
    -0.56
     supérieurs
    -0.52
     normaux
    -0.52
     ocio
    -0.52
     religieuses
    -0.52
     tranquille
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.66
    MessageOf
    0.65
    JsonFormat
    0.61
    RenderAtEndOf
    0.59
     provoc
    0.56
    WebMethod
    0.54
    Bakgrunnsstoff
    0.54
    nościo
    0.52
    InfoWindow
    0.52
     kasarigan
    0.51
    Activations Density 0.020%

    No Known Activations