© 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. 92514
    Prev
    Next
    INDEX
    Explanations

    bodies of water

    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
     water
    -0.49
     pool
    -0.47
     river
    -0.46
    gnac
    -0.46
     fluid
    -0.46
    Jîn
    -0.44
    ToTable
    -0.43
     aquatic
    -0.43
     aquarium
    -0.42
    vič
    -0.42
    POSITIVE LOGITS
     mites
    0.64
     Wiktionnaire
    0.59
     AssemblyCulture
    0.59
    NOPQRST
    0.56
     doInBackground
    0.56
    manship
    0.56
     doigt
    0.55
    izarse
    0.55
    quakes
    0.54
     épaules
    0.54
    Activations Density 0.003%

    No Known Activations