© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72077
    Prev
    Next
    INDEX
    Explanations

    scientific or technical writing

    np_max-act-logits · 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
     }{@
    -0.54
     geholfen
    -0.51
     korun
    -0.48
    antaranya
    -0.48
    bitField
    -0.48
    ignants
    -0.48
     erwarten
    -0.47
     liegen
    -0.46
    namics
    -0.46
    culable
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.71
     slow
    0.70
     lower
    0.70
    IsContent
    0.68
    XmlAccessType
    0.62
    +#+#
    0.61
     block
    0.60
     speed
    0.60
    batore
    0.58
    WebServlet
    0.56
    Activations Density 0.001%

    No Known Activations