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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12251
    Prev
    Next
    INDEX
    Explanations

    technical text about endings

    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
     dieux
    -0.51
    __(/*!
    -0.50
     Lightboxes
    -0.50
     Amend
    -0.49
     Paglinawan
    -0.48
     débats
    -0.48
     Distribute
    -0.47
     Wikimedijinoj
    -0.46
     doInBackground
    -0.46
     Wicidata
    -0.46
    POSITIVE LOGITS
    :✨
    0.81
    othermic
    0.59
    uronic
    0.54
    epiece
    0.54
     vacuum
    0.52
     piece
    0.51
    urable
    0.50
     pieces
    0.50
     utilization
    0.50
    onaceous
    0.50
    Activations Density 0.005%

    No Known Activations