© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38815
    Prev
    Next
    INDEX
    Explanations

    describing a specific topic

    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
    GraphicsUnit
    -0.80
     Capitalism
    -0.80
     iron
    -0.77
    sizeCache
    -0.67
     gynhyrchwyd
    -0.66
    жидан
    -0.62
    errHandler
    -0.61
     RouterModule
    -0.60
     GetEnumerator
    -0.60
    CodeAttribute
    -0.60
    POSITIVE LOGITS
    fraid
    0.49
    ……"
    0.47
     [{
    0.47
    ary
    0.46
     CIC
    0.46
     onCancelled
    0.44
    z
    0.43
     Chriftian
    0.42
     respeito
    0.42
     mln
    0.42
    Activations Density 0.036%

    No Known Activations