© 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. 91132
    Prev
    Next
    INDEX
    Explanations

    strength

    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
     strong
    -1.73
     application
    -1.59
    application
    -1.55
     Strong
    -1.45
    strong
    -1.44
    Strong
    -1.41
     Application
    -1.40
    Application
    -1.39
     stronger
    -1.37
     applications
    -1.35
    POSITIVE LOGITS
    #+#
    0.75
    MigrationBuilder
    0.73
     autorytatywna
    0.66
    aarrggbb
    0.62
     المعيارى
    0.59
     collet
    0.57
     kasarigan
    0.56
     Upland
    0.56
     defaultstate
    0.56
    BITDA
    0.54
    Activations Density 0.089%

    No Known Activations