© 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. 0-CLT-HP
    7. 41328
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · 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
     Efq
    -0.86
     ſtill
    -0.86
     himſelf
    -0.85
     whoſe
    -0.84
     myſelf
    -0.82
     purpoſe
    -0.78
     Anſ
    -0.77
     muſt
    -0.77
     ſta
    -0.77
     juſt
    -0.77
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.73
    NameInMap
    0.68
     MainAxisSize
    0.59
    ंदीखरीदारी
    0.58
    AutoField
    0.54
     }{@
    0.52
    SharedCtor
    0.50
     EnglishChoose
    0.49
    awtextra
    0.49
    StoryboardSegue
    0.48
    Activations Density 2.263%

    No Known Activations