© 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. 5722
    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
    <bos>
    -0.51
    izr
    -0.50
    WriteBarrier
    -0.47
    loving
    -0.46
    ղ
    -0.45
    moveToFirst
    -0.45
    writeFieldEnd
    -0.44
    Externí
    -0.44
    extendable
    -0.43
    tagHelperRunner
    -0.43
    POSITIVE LOGITS
     following
    0.62
     University
    0.60
     Hundred
    0.58
     تانيه
    0.57
     state
    0.57
    Espèce
    0.56
    出版年
    0.54
     незавершена
    0.52
    Largest
    0.52
     above
    0.52
    Activations Density 0.000%

    No Known Activations