© 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. 1-CLT-HP
    7. 12338
    Prev
    Next
    INDEX
    Explanations

    origin

    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
     autorytatywna
    -0.68
    ående
    -0.55
     origin
    -0.54
    rungsseite
    -0.53
    Eloquent
    -0.52
     /\.(
    -0.52
    MessageOf
    -0.50
    ModelAdmin
    -0.49
     mergeFrom
    -0.49
    دانشنامهٔ
    -0.49
    POSITIVE LOGITS
    ыгана
    0.55
    asilkan
    0.54
    ->___
    0.51
    ViewFeatures
    0.50
     Mifflin
    0.49
    CppCodeGen
    0.49
    Mean
    0.48
     McCull
    0.45
    mean
    0.45
     Mean
    0.44
    Activations Density 0.006%

    No Known Activations