© 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. 92059
    Prev
    Next
    INDEX
    Explanations

    notation, symbols

    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
     OFDb
    -0.63
    
    -0.63
    thâu
    -0.54
     initComponents
    -0.54
    Попис
    -0.53
    inSlope
    -0.53
     FetchType
    -0.51
     propOrder
    -0.51
     CreateTagHelper
    -0.50
    awtextra
    -0.49
    POSITIVE LOGITS
     naudoti
    0.63
     pacchetto
    0.60
    ništ
    0.55
     eseguire
    0.54
     Fuhr
    0.54
     compétence
    0.53
     enfans
    0.53
     Gos
    0.52
     usata
    0.51
    RegressionTest
    0.51
    Activations Density 0.002%

    No Known Activations