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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2583
    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
    >--}}
    -0.95
    CppCodeGen
    -0.89
    ].)
    -0.88
    )”.
    -0.87
    +#+#
    -0.81
    "}")
    -0.81
    ),”
    -0.80
    OGND
    -0.80
    GEBURTSDATUM
    -0.80
     дописавши
    -0.79
    POSITIVE LOGITS
    ↵
    0.76
    <eos>
    0.72
    ...
    0.70
     ...
    0.67
     
    0.55
    ....
    0.54
    0.51
    ↵↵
    0.50
    ​
    0.50
    …
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.