© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1563
    Prev
    Next
    INDEX
    Explanations

    to

    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
     saying
    -0.61
     screening
    -0.60
    QMetaType
    -0.59
    databinding
    -0.57
     asking
    -0.56
     showing
    -0.54
     stating
    -0.54
    equilibrio
    -0.54
     proving
    -0.54
    ühnen
    -0.54
    POSITIVE LOGITS
     be
    0.79
    ysacchar
    0.67
     walk
    0.59
     sit
    0.59
     watch
    0.58
     feel
    0.57
     ride
    0.56
     wake
    0.55
     stand
    0.55
     kneel
    0.52
    Activations Density 0.006%

    No Known Activations