© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16221
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    Negative Logits
     (−
    -0.79
    (−
    -0.73
     ​
    -0.72
    发表于
    -0.71
    ​,
    -0.69
    ​.
    -0.68
    <bos>
    -0.68
    ​​​
    -0.67
     referenties
    -0.67
     ≥
    -0.66
    POSITIVE LOGITS
    ”
    0.49
    ”?
    0.42
    ?”
    0.42
     noastre
    0.42
     חיצוניים
    0.39
    kháu
    0.37
     Cupid
    0.36
    ”;
    0.36
     ?”
    0.36
    ”!
    0.34
    Activations Density 0.041%

    No Known Activations