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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5841
    Prev
    Next
    INDEX
    Explanations

    words related to the economic impact of something

    oai_token-act-pair · gemini-2.0-flash

    references to cost-related terms and concepts

    np_token-act-pair-logits · gpt-4o-mini

    cost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    
    -0.71
    ItemBackground
    -0.62
    spesies
    -0.57
    kuuta
    -0.56
    sego
    -0.56
    المشاركات
    -0.55
    ugal
    -0.54
    Clik
    -0.53
    urlpatterns
    -0.53
    Bibliograf
    -0.52
    POSITIVE LOGITS
    ThroughAttribute
    0.50
     centres
    0.49
     centre
    0.47
     margin
    0.47
     hjemme
    0.46
    cenia
    0.46
    DebuggerNonUser
    0.45
    literals
    0.44
    centre
    0.43
    ερ
    0.42
    Activations Density 4.791%

    No Known Activations