© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75816
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    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
    evre
    -0.54
    enderror
    -0.52
     Waray
    -0.49
    euvre
    -0.49
     EClass
    -0.48
     fist
    -0.47
     finger
    -0.47
    quare
    -0.47
     galt
    -0.47
    zufügen
    -0.47
    POSITIVE LOGITS
    ChildScrollView
    0.69
    saraba
    0.67
     RSSSF
    0.63
    InjectAttribute
    0.63
    Rujukan
    0.59
     STOCK
    0.57
    Enllaces
    0.56
    StructEnd
    0.56
    AnchorStyles
    0.54
     ſta
    0.54
    Activations Density 0.001%

    No Known Activations