© 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. 14648
    Prev
    Next
    INDEX
    Explanations

    un

    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
    RRect
    -0.45
    Lịch
    -0.44
    getPassword
    -0.44
    κολου
    -0.43
    GeneratedCode
    -0.41
     logo
    -0.41
    äldrar
    -0.41
     mengam
    -0.41
     rumahnya
    -0.41
    Membership
    -0.40
    POSITIVE LOGITS
    onAttach
    0.71
    writeField
    0.70
    makeConstraints
    0.61
    InjectAttribute
    0.60
    Kontrola
    0.59
    elemField
    0.59
     CreateTagHelper
    0.57
    shakes
    0.55
    Mitchell
    0.54
    JspWriter
    0.54
    Activations Density 0.019%

    No Known Activations