© 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. 91538
    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
    Portale
    -0.79
    ItemBackground
    -0.68
    WebServlet
    -0.63
    RectangleBorder
    -0.63
     useSelector
    -0.62
     Tert
    -0.60
     CreateTagHelper
    -0.59
     reborn
    -0.59
    selho
    -0.58
    EDEFAULT
    -0.57
    POSITIVE LOGITS
    getMenuInflater
    0.50
     Autorizaciones
    0.50
     groote
    0.49
    లాలు
    0.47
     ketahui
    0.47
     avoient
    0.46
     mogelijk
    0.45
    Or
    0.44
     '\\;'
    0.44
     enfans
    0.43
    Activations Density 0.006%

    No Known Activations