© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    non-prose text

    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
    FormTagHelper
    -0.45
    ResumeLayout
    -0.45
    omento
    -0.42
    Diweddarwch
    -0.39
     [...]
    -0.39
     scar
    -0.38
     kast
    -0.38
    klärt
    -0.37
     critical
    -0.37
    farwyddwr
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.73
    
    0.69
     auffi
    0.67
     iſt
    0.66
     gärna
    0.66
     ―――――
    0.63
     stället
    0.63
     Roskov
    0.63
     kvä
    0.63
    ecore
    0.63
    Activations Density 0.050%

    No Known Activations