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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14296
    Prev
    Next
    INDEX
    Explanations

    SQL update statements which change 'name' fields

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    存于互联网档案馆
    -0.58
    ValueStyle
    -0.57
    tonsoft
    -0.52
    --)
    
    -0.50
    AndPassword
    -0.49
    PCell
    -0.49
    Diweddarwch
    -0.48
    >");
    
    -0.47
    '},
    
    -0.47
    بوابة
    -0.46
    POSITIVE LOGITS
    TagMode
    0.67
    bootstrapcdn
    0.66
     vechi
    0.61
    =”
    0.58
    __(/*!
    0.57
     auguri
    0.57
    featureID
    0.55
    =’
    0.55
     onCreateView
    0.55
     Bellini
    0.54
    Activations Density 3.173%

    No Known Activations