© 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. 95016
    Prev
    Next
    INDEX
    Explanations

    Code/Serialized Data

    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
     للاسماء
    -1.05
     autorytatywna
    -0.98
     OFDb
    -0.97
     '\\;'
    -0.96
    XmlAccessorType
    -0.95
    Tembelea
    -0.94
    parsedMessage
    -0.94
    GOTREF
    -0.94
    قایناق‌لار
    -0.91
    MigrationBuilder
    -0.90
    POSITIVE LOGITS
     lourd
    0.41
     žiad
    0.39
     "
    0.39
    '
    0.39
    ere
    0.39
    "
    0.38
    cektir
    0.38
    rather
    0.37
     arrivare
    0.37
     rather
    0.36
    Activations Density 0.003%

    No Known Activations