© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1874
    Prev
    Next
    INDEX
    Explanations

    Contact/Contrast

    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
     contact
    -1.28
    contact
    -1.09
     contacto
    -1.01
     conflict
    -0.93
     force
    -0.91
    conflict
    -0.91
    Contact
    -0.88
     contato
    -0.88
     contatto
    -0.83
     Contact
    -0.82
    POSITIVE LOGITS
    ation
    0.56
    ants
    0.56
     with
    0.55
    ings
    0.54
    ing
    0.53
    ers
    0.52
    parsedMessage
    0.52
     folding
    0.51
     geodesic
    0.51
     coronal
    0.51
    Activations Density 0.049%

    No Known Activations