© 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. 5-CLT-HP
    7. 5150
    Prev
    Next
    INDEX
    Explanations

    0

    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
    AddHtmlAttribute
    -0.68
     hasattr
    -0.54
     holds
    -0.52
     tenders
    -0.52
    dataclass
    -0.49
     plus
    -0.48
    %
    -0.48
    <bos>
    -0.48
     tender
    -0.47
     delic
    -0.47
    POSITIVE LOGITS
     varandra
    0.61
     roulant
    0.60
     vœux
    0.59
     défis
    0.58
     PopupWindow
    0.57
     Grecs
    0.57
     éché
    0.57
     långt
    0.57
     vérit
    0.55
     atualização
    0.55
    Activations Density 0.004%

    No Known Activations