© 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. 39940
    Prev
    Next
    INDEX
    Explanations

    boundaries/containers/scope

    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
     IBOutlet
    -0.56
     nakalista
    -0.56
    Portale
    -0.52
     tillegg
    -0.50
    endswith
    -0.50
    iomanip
    -0.48
     touristes
    -0.48
    Quiénes
    -0.47
     aihe
    -0.47
    ichè
    -0.47
    POSITIVE LOGITS
    @[+][
    0.81
    SharedCtor
    0.66
    PreferredItem
    0.65
     Esper
    0.60
    ItemLayout
    0.60
    RegistryLite
    0.60
    RegressionTest
    0.60
    المشاركات
    0.59
    teps
    0.58
     Quora
    0.58
    Activations Density 0.049%

    No Known Activations