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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    россий
    -0.60
    Obrázky
    -0.58
     minOccurs
    -0.53
    XtraGrid
    -0.48
    CppCodeGen
    -0.48
    DataAnnotations
    -0.47
    IRQn
    -0.47
     ['./
    -0.46
     meet
    -0.45
     utilize
    -0.45
    POSITIVE LOGITS
    findpost
    0.56
    XmlAccessType
    0.54
    migrationBuilder
    0.52
    Autoritní
    0.52
    Géographie
    0.52
    >>()
    0.50
    Хьажоргаш
    0.50
     betweenstory
    0.49
    Koordinaten
    0.49
    //
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.