© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    varied excerpts

    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
     Monfieur
    -0.67
     myſelf
    -0.54
     Borel
    -0.52
     precedes
    -0.49
     piú
    -0.48
     Considered
    -0.47
     epistle
    -0.47
    rsiniz
    -0.47
     itſelf
    -0.45
    ingdon
    -0.45
    POSITIVE LOGITS
    time
    0.98
    tably
    0.89
    teen
    0.88
    fraid
    0.86
    Tikang
    0.81
    aires
    0.79
    selves
    0.79
    poptosis
    0.78
    depend
    0.77
    nemia
    0.75
    Activations Density 0.073%

    No Known Activations