© 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. 38987
    Prev
    Next
    INDEX
    Explanations

    ml

    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
    ml
    -0.72
     ml
    -0.67
     ML
    -0.57
    s
    -0.54
    ML
    -0.51
    ill
    -0.49
    mL
    -0.48
    assert
    -0.47
     assembly
    -0.46
     assert
    -0.46
    POSITIVE LOGITS
    AccessorTable
    1.13
     дописавши
    1.10
    yntaxException
    1.10
     mergeFrom
    1.06
     MessageBoxIcon
    1.05
    GraphicsUnit
    1.05
     kasarigan
    1.02
    UnitTesting
    1.02
    OGND
    0.98
    IsContent
    0.97
    Activations Density 0.352%

    No Known Activations