© 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. 16268
    Prev
    Next
    INDEX
    Explanations

    addresses

    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
    IntoConstraints
    -0.89
     مشين
    -0.84
     يتيمه
    -0.79
    StoryboardSegue
    -0.78
    Hochspringen
    -0.74
     الحره
    -0.71
    parsedMessage
    -0.71
    цездатний
    -0.71
     незавершена
    -0.71
    OGND
    -0.71
    POSITIVE LOGITS
    ’
    0.48
    '
    0.46
    ,
    0.44
     call
    0.44
    /
    0.42
     nonetheless
    0.42
    .
    0.40
     even
    0.39
     alone
    0.39
    ↵↵
    0.38
    Activations Density 0.065%

    No Known Activations