© 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. 2656
    Prev
    Next
    INDEX
    Explanations

    Parenthetical phrases or lists

    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
    styleable
    -0.64
    Portail
    -0.63
    GEBURTS
    -0.63
    mybatisplus
    -0.57
    forRoot
    -0.56
    Portale
    -0.55
     propOrder
    -0.55
     noDo
    -0.53
    has
    -0.51
     Савезне
    -0.51
    POSITIVE LOGITS
    upan
    0.52
    InternalFrame
    0.48
    harvest
    0.47
     irrig
    0.47
    coating
    0.47
    helix
    0.47
     Title
    0.46
     getTitle
    0.45
    efit
    0.45
     TITLE
    0.45
    Activations Density 0.004%

    No Known Activations