© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93227
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .
    -0.54
    '
    -0.51
     or
    -0.49
    –
    -0.47
    -
    -0.47
    <eos>
    -0.47
    /
    -0.47
    ↵
    -0.44
     B
    -0.43
     easy
    -0.43
    POSITIVE LOGITS
     >=",
    1.27
     يتيمه
    1.15
     ویکی‌پدیای
    1.07
    )";
    1.04
     Мексичка
    1.04
    ]--;
    1.04
    TintMode
    1.00
    expandindo
    0.99
    ########.
    0.98
     AssemblyTitle
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.