© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94643
    Prev
    Next
    INDEX
    Explanations

    head

    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
     head
    -2.63
     Head
    -1.89
     heads
    -1.67
    Head
    -1.63
     HEAD
    -1.52
    head
    -1.32
     cabeza
    -1.27
     father
    -1.23
     kepala
    -1.23
    HEAD
    -1.20
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
    guards
    0.75
    piece
    0.74
    backers
    0.73
    masters
    0.71
    Билгалдахарш
    0.71
    guard
    0.71
     AssemblyVersion
    0.69
    finding
    0.69
    wolves
    0.69
    Activations Density 0.245%

    No Known Activations