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. 11227
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
     Carbon
    -0.57
     carbon
    -0.54
    Rptr
    -0.53
    PlayerController
    -0.50
    auso
    -0.49
    imai
    -0.48
    guió
    -0.48
    ÓS
    -0.47
    lysses
    -0.47
     Naked
    -0.47
    POSITIVE LOGITS
     виправивши
    0.67
    msgTypes
    0.64
    tableFuture
    0.62
    protoimpl
    0.60
     "..\..\..\
    0.59
    
    
    0.57
    featureID
    0.57
    preter
    0.56
     propOrder
    0.55
    migrationBuilder
    0.54
    Activations Density 0.097%

    No Known Activations