© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95062
    Prev
    Next
    INDEX
    Explanations

    Nationalities

    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
     BoxFit
    -0.79
     ostavi
    -0.78
    GraphicsUnit
    -0.76
     Inventories
    -0.73
    RectangleBorder
    -0.73
    ponses
    -0.72
     JpaRepository
    -0.72
     мәкал
    -0.70
    interopRequire
    -0.69
    MessageTagHelper
    -0.69
    POSITIVE LOGITS
     and
    0.56
     men
    0.47
     school
    0.46
     war
    0.41
    stackSize
    0.40
     construction
    0.39
     poli
    0.39
     college
    0.38
     model
    0.36
     shop
    0.35
    Activations Density 0.001%

    No Known Activations