© 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. 20-CLT-HP
    7. 74632
    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
    uxxxx
    -0.52
    KindOfClass
    -0.49
    complexContent
    -0.48
    fortawesome
    -0.46
     ControllerBase
    -0.45
     Autorizaciones
    -0.44
    XmlAccessType
    -0.44
    ஐ
    -0.44
    son
    -0.42
    Kann
    -0.42
    POSITIVE LOGITS
    writeFieldEnd
    0.63
    новниш
    0.59
    InjectAttribute
    0.57
    istoitu
    0.57
     Exacts
    0.57
     allAfrica
    0.56
    الحياه
    0.55
    kháu
    0.55
    fillType
    0.54
    verwijspagina
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.