© 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. 2112
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    verwijspagina
    -0.73
     informée
    -0.71
     للمعارف
    -0.70
    WithIOException
    -0.64
    afficheront
    -0.61
     noDo
    -0.60
    ConstraintMaker
    -0.59
    Rujuakan
    -0.58
    QMetaType
    -0.57
     initComponents
    -0.56
    POSITIVE LOGITS
    LabelTagHelper
    0.52
     asyncio
    0.46
    ühnen
    0.44
    capan
    0.43
    leftrightarrow
    0.42
     Southwestern
    0.41
     '\\;'
    0.41
    HttpStatus
    0.41
    wild
    0.41
     skr
    0.41
    Activations Density 0.006%

    No Known Activations