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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16382
    Prev
    Next
    INDEX
    Explanations

    angle brackets and inequalities in code snippets or mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Math/code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    basicConfig
    -0.59
     <<<<<<<<<<<<<<
    -0.56
    writeField
    -0.51
    abstractmethod
    -0.50
    logrus
    -0.46
     useDispatch
    -0.45
     kiện
    -0.44
    accesso
    -0.42
     Exactos
    -0.42
    eqn
    -0.41
    POSITIVE LOGITS
    دانشنامهٔ
    0.90
    ")){
    
    0.70
    }');
    0.64
    kmale
    0.63
    ')){
    0.63
     ]
    
    0.63
    PyExc
    0.61
    '){
    
    0.61
     utafitiHapana
    0.60
    queryInterface
    0.60
    Activations Density 4.208%

    No Known Activations