© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90828
    Prev
    Next
    INDEX
    Explanations

    {

    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
    ↵
    -0.69
     T
    -0.54
     L
    -0.52
     Th
    -0.52
    <eos>
    -0.50
     "
    -0.50
     $
    -0.50
     th
    -0.49
     She
    -0.48
     we
    -0.47
    POSITIVE LOGITS
     Theſe
    0.89
     Efq
    0.83
     itſelf
    0.82
     estimés
    0.82
     Jefus
    0.79
     ſche
    0.78
     Houſe
    0.77
    enumi
    0.76
     sanitaires
    0.76
     Eſ
    0.75
    Activations Density 0.189%

    No Known Activations