© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91023
    Prev
    Next
    INDEX
    Explanations

    technical/medical text snippets

    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
    Negative Logits
    RenderAtEndOf
    -0.63
     OTHERWISE
    -0.46
    ̍t
    -0.46
    lorn
    -0.45
    первых
    -0.45
     pied
    -0.44
    Spire
    -0.44
    đi
    -0.43
     επί
    -0.43
    shortest
    -0.42
    POSITIVE LOGITS
    parsedMessage
    0.83
     HasFactory
    0.74
     ProtoMessage
    0.73
     ComVisible
    0.69
    jsxFileName
    0.68
    StoreMessageInfo
    0.68
     initComponents
    0.66
    SourceChecksum
    0.65
    //-->
    0.63
     aDecoder
    0.62
    Activations Density 0.001%

    No Known Activations