© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95007
    Prev
    Next
    INDEX
    Explanations

    mop

    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
    TagMode
    -0.91
    DockStyle
    -0.88
    Personendaten
    -0.85
    WebVitals
    -0.81
     مشين
    -0.77
     MainAxisSize
    -0.75
     تضيفلها
    -0.73
    anskje
    -0.73
     كومونز
    -0.73
     незавершена
    -0.73
    POSITIVE LOGITS
    ness
    0.88
    ies
    0.88
    ie
    0.84
    ier
    0.83
    st
    0.81
    el
    0.81
    ed
    0.81
    ings
    0.79
    ers
    0.78
    ist
    0.77
    Activations Density 0.046%

    No Known Activations