© 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. 5-CLT-HP
    7. 91244
    Prev
    Next
    INDEX
    Explanations

    s

    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
    uxxxx
    -0.67
    llum
    -0.67
    ussis
    -0.66
     Chartres
    -0.64
     Athenians
    -0.63
     BFS
    -0.61
     Koran
    -0.60
     Reichstag
    -0.60
    fromnode
    -0.59
     Charlemagne
    -0.58
    POSITIVE LOGITS
    DockStyle
    0.63
     great
    0.50
    hiel
    0.46
     ujednoznacz
    0.45
    ⓘ
    0.45
    makeConstraints
    0.44
     sc
    0.43
    InstrumentedTest
    0.43
     perd
    0.42
    ciss
    0.41
    Activations Density 0.002%

    No Known Activations