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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1561
    Prev
    Next
    INDEX
    Explanations

    mentions of Middle Eastern countries and the relationships between them

    oai_token-act-pair · gemini-2.0-flash

    Middle East conflicts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     EconPapers
    -1.03
     defaultstate
    -0.74
    uxxxx
    -0.72
     onCancelled
    -0.71
     betweenstory
    -0.71
    Jeografia
    -0.69
    ########.
    -0.64
     Oman
    -0.63
     PyTuple
    -0.62
     चीज़ों
    -0.60
    POSITIVE LOGITS
    SourceChecksum
    0.47
    outState
    0.44
    featureID
    0.44
    aui
    0.44
    @",
    0.43
    <_>
    0.43
     tavolo
    0.42
     гори
    0.41
     Hauteur
    0.41
    ddar
    0.41
    Activations Density 5.059%

    No Known Activations