© 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. 73730
    Prev
    Next
    INDEX
    Explanations

    York

    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
     Queens
    -0.69
     Flushing
    -0.69
     queens
    -0.68
     Kasper
    -0.66
     KINGS
    -0.63
     juniors
    -0.60
     Kings
    -0.59
     Kamil
    -0.59
     Borough
    -0.59
     QUE
    -0.56
    POSITIVE LOGITS
     utafitiHapana
    0.54
    ContentAsync
    0.51
    الحياه
    0.50
    }]{
    0.50
    PRNewswire
    0.49
    HasForeignKey
    0.47
     useAppContext
    0.47
    ModelSerializer
    0.46
    abstractmethod
    0.45
    awtextra
    0.44
    Activations Density 0.001%

    No Known Activations