© 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. 77512
    Prev
    Next
    INDEX
    Explanations

    academic and research papers

    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
     Waray
    -0.86
    脚注の使い方
    -0.69
     cherchés
    -0.69
    Alike
    -0.60
     transfieras
    -0.60
     Ghetto
    -0.60
     Lightboxes
    -0.60
     برانيه
    -0.60
    ंदीखरीदारी
    -0.59
    achella
    -0.59
    POSITIVE LOGITS
    ้อม
    0.45
    presso
    0.42
    wd
    0.40
    FieldBuilder
    0.40
    closePath
    0.40
    ους
    0.38
    bundet
    0.37
    kannya
    0.37
    guió
    0.37
     vezes
    0.37
    Activations Density 0.000%

    No Known Activations