© 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. 5-CLT-HP
    7. 6207
    Prev
    Next
    INDEX
    Explanations

    moth

    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
    '
    -0.59
    </b>
    -0.57
    .
    -0.54
    ↵↵
    -0.50
    SqlClient
    -0.50
    ;
    -0.49
     са
    -0.47
    AppBar
    -0.47
    //}
    -0.46
    ↵↵↵↵
    -0.45
    POSITIVE LOGITS
     purpoſe
    0.87
     preſent
    0.84
     Theſe
    0.83
     ſtate
    0.82
     ſhall
    0.81
     leaſt
    0.81
     cauſe
    0.80
     faſt
    0.79
     uſe
    0.78
     ſte
    0.78
    Activations Density 0.053%

    No Known Activations