© 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. 1-CLT-HP
    7. 10102
    Prev
    Next
    INDEX
    Explanations

    medical/scientific experiments

    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
     يتيمه
    -0.70
    ibatis
    -0.67
    setVerticalGroup
    -0.66
    ResumeLayout
    -0.65
     initComponents
    -0.64
    RetentionPolicy
    -0.63
     estekak
    -0.62
     MainAxisSize
    -0.61
    MessageTagHelper
    -0.61
    buttonBar
    -0.61
    POSITIVE LOGITS
    ing
    0.55
    ed
    0.48
    躇
    0.45
     cebo
    0.43
    arken
    0.43
    hoge
    0.43
    되어
    0.42
     cubanos
    0.41
     Stich
    0.40
     незавершена
    0.40
    Activations Density 0.046%

    No Known Activations