© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91959
    Prev
    Next
    INDEX
    Explanations

    Measuring

    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
     AssemblyProduct
    -0.80
    STON
    -0.78
     Measuring
    -0.78
    Measuring
    -0.75
    ston
    -0.71
     rays
    -0.69
     présidenti
    -0.68
     hanem
    -0.66
    ]<<"
    -0.62
    measuring
    -0.61
    POSITIVE LOGITS
    клопе
    0.54
    principalColumn
    0.49
     المعيارى
    0.47
    бовать
    0.47
    #+#
    0.46
    Hochspringen
    0.45
    bors
    0.45
    diff
    0.44
    게
    0.44
    rt
    0.42
    Activations Density 0.065%

    No Known Activations