© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74781
    Prev
    Next
    INDEX
    Explanations

    Code and errors

    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
    Malley
    -0.45
    Хьажоргаш
    -0.43
    SharedDtor
    -0.42
    glas
    -0.41
     Classi
    -0.40
    UITableView
    -0.40
     insuffisamment
    -0.40
    mojo
    -0.40
    ItemLayout
    -0.39
     snippetHide
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    0.84
    AndEndTag
    0.66
    AddHtmlAttribute
    0.60
     متعلقه
    0.60
    estors
    0.59
    MLLoader
    0.59
    endphp
    0.59
    tonsoft
    0.59
     للمعارف
    0.56
     rhestr
    0.56
    Activations Density 0.001%

    No Known Activations