© 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. 4-CLT-HP
    7. 555
    Prev
    Next
    INDEX
    Explanations

    containment

    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
    ArrowToggle
    -1.01
    Décès
    -0.87
    tagHelperRunner
    -0.85
    :✨
    -0.82
    Diwedd
    -0.77
     nahilalakip
    -0.73
    __(/*!
    -0.73
     initComponents
    -0.72
    AndEndTag
    -0.71
     Италијани
    -0.71
    POSITIVE LOGITS
     Pauly
    0.44
    wór
    0.42
     concrete
    0.42
    bildung
    0.38
    calyp
    0.36
    concrete
    0.35
    länge
    0.35
     Zucker
    0.35
    öffentlichungen
    0.35
     point
    0.34
    Activations Density 0.002%

    No Known Activations