© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92622
    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
    <eos>
    -0.56
    ↵↵
    -0.50
     "
    -0.47
    j
    -0.46
     The
    -0.46
     i
    -0.46
    ↵
    -0.46
    주
    -0.44
    </strong>
    -0.43
    _
    -0.43
    POSITIVE LOGITS
    +#+#
    1.16
    MigrationBuilder
    1.09
    IntoConstraints
    1.05
    MemoryWarning
    1.04
    parsedMessage
    0.95
    IsMutable
    0.91
    findpost
    0.90
    ValueStyle
    0.89
     للمعارف
    0.88
    awtextra
    0.86
    Activations Density 0.000%

    No Known Activations