© 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. 4-CLT-HP
    7. 2526
    Prev
    Next
    INDEX
    Explanations

    Programming/technical documentation

    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
    "}>
    -0.48
    {(-
    -0.48
     "")
    -0.48
    ']))
    -0.48
    ẠI
    -0.47
    IENTE
    -0.47
    ardes
    -0.46
    ARROLL
    -0.45
    ANTE
    -0.45
    iate
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    principalColumn
    0.62
    HasAnnotation
    0.61
    lemény
    0.60
    IntoConstraints
    0.59
     pomeriggio
    0.59
    viembre
    0.58
    paravant
    0.57
     prière
    0.57
    כשיו
    0.56
    Activations Density 0.001%

    No Known Activations