© 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. 15683
    Prev
    Next
    INDEX
    Explanations

    time units

    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
    classnames
    -0.58
     DBNull
    -0.56
    indd
    -0.56
     StatefulWidget
    -0.55
     Jekyll
    -0.54
    reportWebVitals
    -0.53
    ReusableCell
    -0.53
     Cervantes
    -0.52
    culosis
    -0.51
     IBOutlet
    -0.50
    POSITIVE LOGITS
     linkovi
    0.65
    saraba
    0.63
     Paglinawan
    0.57
    pædia
    0.55
    ształ
    0.53
    在哪里
    0.51
    Bef
    0.51
     uska
    0.50
    trab
    0.50
    tiko
    0.50
    Activations Density 0.035%

    No Known Activations