© 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. 0-CLT-HP
    7. 92074
    Prev
    Next
    INDEX
    Explanations

    description

    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
     description
    -1.34
     designation
    -1.24
     Description
    -1.20
    Description
    -1.13
     descripción
    -1.11
    description
    -1.09
     descrizione
    -1.09
     Descriptions
    -1.07
    Descriptions
    -1.06
     Beschreibung
    -1.04
    POSITIVE LOGITS
     EconPapers
    0.86
    Personensuche
    0.82
     tartalomajánló
    0.69
    AccessorTable
    0.69
    Personendaten
    0.66
     AssemblyTitle
    0.66
    AndEndTag
    0.63
    ThroughAttribute
    0.62
    Vidite
    0.62
     للاسماء
    0.62
    Activations Density 0.197%

    No Known Activations