© 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. 1-CLT-HP
    7. 15516
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
     moor
    -1.46
     mooring
    -0.91
     Moor
    -0.83
    moor
    -0.75
    Moor
    -0.75
     moored
    -0.72
     typelib
    -0.65
     lccn
    -0.63
    findpost
    -0.62
     المعيارى
    -0.61
    POSITIVE LOGITS
    ings
    0.58
    haden
    0.52
    land
    0.50
    head
    0.50
    cock
    0.49
    hens
    0.47
    puff
    0.47
    cocks
    0.47
    hood
    0.45
    band
    0.44
    Activations Density 0.009%

    No Known Activations