© 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. 20-CLT-HP
    7. 77548
    Prev
    Next
    INDEX
    Explanations

    programming/rare words

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     generalised
    -0.61
    entary
    -0.60
     apologised
    -0.60
     يتيمه
    -0.58
    MessageOf
    -0.58
    putan
    -0.56
    couverte
    -0.56
     Utili
    -0.55
    adpleegd
    -0.54
     Missed
    -0.54
    POSITIVE LOGITS
    SBATCH
    0.57
     ๆ
    0.48
    WebVitals
    0.44
    medriver
    0.43
     laiton
    0.43
    HtmlAttribute
    0.42
    </tfoot>
    0.42
     practically
    0.41
     jButton
    0.41
     céré
    0.41
    Activations Density 0.000%

    No Known Activations