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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73917
    Prev
    Next
    INDEX
    Explanations

    lympho

    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
    GEBURTSDATUM
    -0.66
    MigrationBuilder
    -0.59
    CloseOperation
    -0.53
    enderror
    -0.53
     चीज़ों
    -0.52
    foundland
    -0.52
     cref
    -0.52
    SpringBootTest
    -0.52
     Fortun
    -0.49
    thodon
    -0.49
    POSITIVE LOGITS
    پیوند
    0.53
    ⓧ
    0.51
    InstanceState
    0.51
    ISupport
    0.50
    cyd
    0.49
    ProgressHUD
    0.47
     flyknit
    0.46
    pacs
    0.46
    penia
    0.46
     مرئيه
    0.45
    Activations Density 0.006%

    No Known Activations