Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74088
    Prev
    Next
    INDEX
    Explanations

    pressure

    np_max-act-logits · 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
    TagMode
    -0.65
    kuuta
    -0.65
    цездатний
    -0.63
     HttpNotFound
    -0.58
     BoxFit
    -0.57
    AndroidJUnit
    -0.57
     Waray
    -0.56
     BorderSide
    -0.56
    pox
    -0.55
    arean
    -0.55
    POSITIVE LOGITS
     pressure
    0.75
    pressure
    0.63
     Pressure
    0.63
     PRESSURE
    0.61
    Pressure
    0.56
     pressão
    0.56
     presión
    0.54
     pressione
    0.49
     pressures
    0.49
     rice
    0.48
    Activations Density 0.001%

    No Known Activations