© 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. 96265
    Prev
    Next
    INDEX
    Explanations

    beneath

    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
    ArgsConstructor
    -0.95
    httphttps
    -0.82
    DockStyle
    -0.75
    uxxxx
    -0.75
    IsContent
    -0.74
    (!__
    -0.73
    RegressionTest
    -0.71
     CreateTagHelper
    -0.68
     OFDb
    -0.68
    ⓧ
    -0.65
    POSITIVE LOGITS
     rivière
    0.44
     not
    0.44
     and
    0.44
     with
    0.43
    urlpatterns
    0.43
     aérea
    0.42
     виправивши
    0.41
     
    0.40
     <
    0.40
     ansatte
    0.40
    Activations Density 0.001%

    No Known Activations