© 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. 92226
    Prev
    Next
    INDEX
    Explanations

    may might

    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
    brainly
    -0.71
    XmlAccessType
    -0.63
    SequentialGroup
    -0.63
    !*\
    -0.61
     jdbcTemplate
    -0.58
     BorderRadius
    -0.56
    gator
    -0.56
    ACGIH
    -0.55
     استنادى
    -0.55
     vectorielles
    -0.55
    POSITIVE LOGITS
     kill
    0.64
    apunov
    0.59
    kill
    0.56
     die
    0.50
    Kill
    0.50
    die
    0.50
    save
    0.48
    do
    0.48
     ویکی‌پدیا
    0.48
     Kill
    0.48
    Activations Density 0.020%

    No Known Activations