© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39841
    Prev
    Next
    INDEX
    Explanations

    Organizations and Locations

    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
     Term
    -0.65
     <<<<<<<<<<<<<<
    -0.65
    
    -0.55
    INE
    -0.55
     Childhood
    -0.55
    CopyWith
    -0.55
    Term
    -0.54
    anke
    -0.54
    发表于
    -0.52
    enties
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.59
    principalColumn
    0.58
    tagHelperRunner
    0.53
    بوابة
    0.52
    ಿಕ
    0.52
    igreja
    0.52
    gents
    0.51
    ExtendWith
    0.51
     Cronin
    0.51
    mii
    0.50
    Activations Density 0.292%

    No Known Activations