© 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. 72663
    Prev
    Next
    INDEX
    Explanations

    technical/varied text

    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
     חיצוניים
    -0.75
    الإنجليزية
    -0.70
     يتيمه
    -0.67
    Vidite
    -0.67
    RegistryLite
    -0.66
    Bibliographie
    -0.66
     réfugiés
    -0.66
     Capture
    -0.65
     الرياضيه
    -0.65
     démocratie
    -0.64
    POSITIVE LOGITS
    findpost
    0.51
    OrNil
    0.43
    HtmlAttribute
    0.42
    Job
    0.39
     Job
    0.38
    DeleteBehavior
    0.38
    ms
    0.38
    mey
    0.36
    тата
    0.36
     Hombre
    0.34
    Activations Density 0.003%

    No Known Activations