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. 1-CLT-HP
    4. 11010
    Prev
    Next
    INDEX
    Explanations

    China

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -0.46
    R
    -0.45
     R
    -0.44
     ‘
    -0.44
     ragion
    -0.42
     [
    -0.42
    sub
    -0.42
    ధ
    -0.42
    der
    -0.42
     f
    -0.41
    POSITIVE LOGITS
     Italijanski
    0.81
     дописавши
    0.76
    NUMX
    0.73
     الرياضيه
    0.72
    featureID
    0.72
     Taipei
    0.71
    Бахар
    0.70
     myſelf
    0.70
    '}>
    0.70
    parsedMessage
    0.68
    Activations Density 0.016%

    No Known Activations