© 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. 5097
    Prev
    Next
    INDEX
    Explanations

    code

    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
    +#+
    -0.61
    ']))
    -0.60
    帖最后由
    -0.58
     Jefus
    -0.57
     Italijanski
    -0.57
    ::_('
    -0.55
     betweenstory
    -0.54
    HtmlAttribute
    -0.53
    )"),
    -0.52
     propOrder
    -0.52
    POSITIVE LOGITS
     Initialized
    0.50
     onData
    0.48
    ostream
    0.48
    рти
    0.45
     talleres
    0.45
    Camp
    0.45
    InputBorder
    0.45
    Personendaten
    0.45
    dotti
    0.45
     anda
    0.45
    Activations Density 0.002%

    No Known Activations