© 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. 72285
    Prev
    Next
    INDEX
    Explanations

    Unix

    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
    الإنجليزية
    -0.60
    RectangleBorder
    -0.60
    verwijspagina
    -0.56
    خابات
    -0.54
    migrationBuilder
    -0.54
    MLLoader
    -0.52
     Cir
    -0.52
    lamabad
    -0.51
    mybatisplus
    -0.51
     doInBackground
    -0.49
    POSITIVE LOGITS
    TemporalType
    0.55
    AndEndTag
    0.54
     AT
    0.54
    󠁢
    0.52
     intptr
    0.52
     ken
    0.49
     Ken
    0.48
     TextInputType
    0.48
    êques
    0.48
     فريبيس
    0.46
    Activations Density 0.002%

    No Known Activations