© 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. 5-CLT-HP
    7. 5700
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    DropColumn
    -0.52
     ensuring
    -0.52
    consulté
    -0.51
     expressed
    -0.51
     AGA
    -0.50
    assertRaises
    -0.50
     meaning
    -0.50
    testify
    -0.49
     promised
    -0.49
    TagHelpers
    -0.49
    POSITIVE LOGITS
    TagMode
    0.49
    etheless
    0.49
     utafitiHapana
    0.47
    例句
    0.45
     entanto
    0.44
    uttavia
    0.43
     CreateTagHelper
    0.42
    -------
    0.42
     ArrayAdapter
    0.41
     Europe
    0.40
    Activations Density 0.003%

    No Known Activations