© 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. 1-CLT-HP
    7. 9681
    Prev
    Next
    INDEX
    Explanations

    plu

    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
    ChildScrollView
    -0.76
    <bos>
    -0.61
     tasche
    -0.54
     pioggia
    -0.54
     déchir
    -0.53
     föruts
    -0.51
     Ră
    -0.51
     Bucure
    -0.50
     käs
    -0.50
     række
    -0.50
    POSITIVE LOGITS
    bootstrapcdn
    0.67
    Rhestr
    0.67
    Демографія
    0.57
    WebVitals
    0.56
     defaultstate
    0.56
     الرياضيه
    0.53
    MessageOf
    0.53
    NullCheck
    0.53
    XmlAccessType
    0.52
    ✨:
    0.52
    Activations Density 0.057%

    No Known Activations