© 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. 76655
    Prev
    Next
    INDEX
    Explanations

    Paran

    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
     समीक्षाओं
    -0.57
    MLLoader
    -0.54
     devil
    -0.52
    quelize
    -0.51
     createState
    -0.49
     InputDecoration
    -0.49
     Scarecrow
    -0.48
    årige
    -0.48
     Rake
    -0.48
     mire
    -0.47
    POSITIVE LOGITS
    ster
    0.59
    Hochspringen
    0.56
    Kaynakça
    0.51
    getItemId
    0.50
     oprot
    0.50
     חיצוניים
    0.49
    STER
    0.49
    sterna
    0.49
    TestBed
    0.49
    Przypisy
    0.48
    Activations Density 0.000%

    No Known Activations