© 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. 96192
    Prev
    Next
    INDEX
    Explanations

    online discussions

    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
     is
    -0.91
    的是
    -0.66
    的就是
    -0.57
     Is
    -0.56
     dokładnie
    -0.56
    adalah
    -0.53
     adalah
    -0.52
     Eintrag
    -0.51
    andria
    -0.51
     IS
    -0.51
    POSITIVE LOGITS
    CppCodeGen
    0.78
    AccessorTable
    0.77
    AndEndTag
    0.73
     otomatig
    0.72
    StoryboardSegue
    0.71
    ScopeManager
    0.71
    RectangleBorder
    0.70
    verwijspagina
    0.68
    IsContent
    0.67
    MigrationBuilder
    0.67
    Activations Density 0.005%

    No Known Activations