© 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. 0-CLT-HP
    7. 92946
    Prev
    Next
    INDEX
    Explanations

    pton

    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
     myſelf
    -1.05
    ſelves
    -1.05
     Majefty
    -1.05
     itſelf
    -1.00
     setter
    -0.99
     Jefus
    -0.97
     poffible
    -0.97
     Monfieur
    -0.95
     leaſt
    -0.95
     Chriftian
    -0.95
    POSITIVE LOGITS
    s
    0.65
    a
    0.61
     ujednoznacz
    0.58
    sb
    0.57
    sl
    0.52
    gl
    0.49
    o
    0.48
    space
    0.45
    spa
    0.45
    sj
    0.45
    Activations Density 0.180%

    No Known Activations