© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96046
    Prev
    Next
    INDEX
    Explanations

    time

    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
     للمعارف
    -0.75
     للاسماء
    -0.73
     يتيمه
    -0.68
    yskland
    -0.61
    lihood
    -0.60
    RRect
    -0.58
    CppCodeGen
    -0.57
    \}\\
    -0.57
     Technicians
    -0.56
    曖昧さ回避
    -0.55
    POSITIVE LOGITS
    legi
    0.50
     or
    0.47
    XmlAccessType
    0.46
    migrationBuilder
    0.45
     drop
    0.44
     Drop
    0.43
    Drop
    0.43
    Queryable
    0.42
    aritions
    0.42
    غيل
    0.41
    Activations Density 0.000%

    No Known Activations