© 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. 92056
    Prev
    Next
    INDEX
    Explanations

    sinter

    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
    endphp
    -1.03
    IntoConstraints
    -0.98
    itinéraire
    -0.79
    XmlAccessorType
    -0.78
    urlpatterns
    -0.77
    AddTagHelper
    -0.75
    SpringBootTest
    -0.69
    TestingModule
    -0.69
    Билгалдахарш
    -0.66
     ModelExpression
    -0.65
    POSITIVE LOGITS
    chard
    0.53
     //$
    0.51
    culable
    0.50
    са
    0.50
     分
    0.49
    psin
    0.49
    Maak
    0.48
    zlo
    0.48
    разуме
    0.47
    ama
    0.46
    Activations Density 0.316%

    No Known Activations