© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38542
    Prev
    Next
    INDEX
    Explanations

    a

    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
     a
    -0.94
     église
    -0.83
     esperienza
    -0.79
     île
    -0.79
     âge
    -0.78
     école
    -0.78
     azione
    -0.77
     altri
    -0.76
     attività
    -0.76
     affrontare
    -0.76
    POSITIVE LOGITS
     lot
    0.79
    poptosis
    0.65
    verages
    0.63
     subset
    0.58
    imed
    0.57
     series
    0.56
     variety
    0.55
    eronau
    0.55
    septic
    0.55
    fraid
    0.54
    Activations Density 0.060%

    No Known Activations