© 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. 92244
    Prev
    Next
    INDEX
    Explanations

    Law and business

    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
    TRIBUN
    -0.68
     for
    -0.66
    ivir
    -0.60
     出版
    -0.53
    ohol
    -0.52
    SenderId
    -0.52
    holt
    -0.52
    isition
    -0.52
    出版年
    -0.51
     Tip
    -0.50
    POSITIVE LOGITS
     themselves
    0.66
     ourselves
    0.65
    AnchorStyles
    0.60
     yourselves
    0.59
     thyself
    0.56
     yourself
    0.56
     herself
    0.56
    \{\\
    0.55
    selves
    0.52
     zichzelf
    0.52
    Activations Density 0.010%

    No Known Activations