Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74483
    Prev
    Next
    INDEX
    Explanations

    Coding/file names

    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
    ch
    -0.68
    UIControlState
    -0.66
     NUKAT
    -0.61
    ]")]
    -0.57
    ConstraintMaker
    -0.55
    meros
    -0.54
    SharedCtor
    -0.52
    ContentAsync
    -0.52
    ItemLayout
    -0.52
    aarrggbb
    -0.51
    POSITIVE LOGITS
    BeginContext
    0.54
    олові
    0.54
    w
    0.50
    पया
    0.50
    tagHelperRunner
    0.48
     "..\..\..\
    0.48
    adpleegd
    0.47
    TypedDataSet
    0.46
    BeforeClass
    0.46
     Paglinawan
    0.44
    Activations Density 0.011%

    No Known Activations