© 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. 4-CLT-HP
    7. 2998
    Prev
    Next
    INDEX
    Explanations

    es

    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
    Lindo
    -0.52
     field
    -0.52
     each
    -0.51
     sal
    -0.48
     चुनें
    -0.48
     sportivo
    -0.48
     lume
    -0.47
    occuper
    -0.47
     salt
    -0.45
     Halls
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.66
    TagMode
    0.60
    SourceChecksum
    0.60
    av
    0.54
     createSprite
    0.54
     ModelExpression
    0.53
    HasForeignKey
    0.52
     Signalez
    0.52
    complexType
    0.51
    FormTagHelper
    0.51
    Activations Density 0.008%

    No Known Activations