© 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. 41738
    Prev
    Next
    INDEX
    Explanations

    locations and groups of people

    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
     Fukushima
    -0.99
     estekak
    -0.97
    setVerticalGroup
    -0.91
     itſelf
    -0.91
     iſt
    -0.90
    OGND
    -0.88
    ReusableCell
    -0.88
     ſind
    -0.88
    ambique
    -0.84
     дописавши
    -0.83
    POSITIVE LOGITS
     So
    0.57
    ’
    0.54
     
    0.51
     And
    0.48
     Bar
    0.48
     Now
    0.46
    '
    0.45
     Key
    0.45
     Lee
    0.45
     Man
    0.43
    Activations Density 0.129%

    No Known Activations