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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16276
    Prev
    Next
    INDEX
    Explanations

    words related to government economic and social policy

    oai_token-act-pair · gemini-2.0-flash

    Social, economic, and political

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     BoxDecoration
    -0.56
    Vidite
    -0.56
     فريبيس
    -0.56
    Personendaten
    -0.54
     kaarangay
    -0.53
    DataAnnotations
    -0.52
     BoxFit
    -0.52
     <=",
    -0.52
    setViewportView
    -0.51
    "]];
    -0.51
    POSITIVE LOGITS
    jahtera
    0.50
     security
    0.49
     <<<<<<<<<<<<<<
    0.48
    multicolumn
    0.48
    GoogleApiClient
    0.47
     defStyle
    0.46
     climatic
    0.46
     economic
    0.45
     polícia
    0.45
     jurisprudence
    0.44
    Activations Density 6.333%

    No Known Activations