© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    Code/URLs

    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
     OFDb
    -0.65
     propOrder
    -0.57
    Gambas
    -0.53
    MigrationBuilder
    -0.50
    XmlAccessorType
    -0.49
    EClass
    -0.48
    sidemargin
    -0.48
    XmlType
    -0.47
     &___
    -0.46
    contentLoaded
    -0.45
    POSITIVE LOGITS
     ferons
    0.66
    شوف
    0.65
     églises
    0.65
     erreurs
    0.63
     courants
    0.63
     stabilité
    0.62
     preuves
    0.60
    ranean
    0.60
     verrez
    0.59
     meubles
    0.59
    Activations Density 0.123%

    No Known Activations