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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1807
    Prev
    Next
    INDEX
    Explanations

    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
     zelve
    -0.95
     seguenti
    -0.78
     isInitialized
    -0.77
     itself
    -0.77
    ArgsConstructor
    -0.76
    :+:
    -0.76
     désolés
    -0.75
     répondit
    -0.73
     nemico
    -0.72
     nahilalakip
    -0.72
    POSITIVE LOGITS
     case
    0.48
     office
    0.47
    /
    0.47
    -
    0.45
     site
    0.45
     branch
    0.45
     solar
    0.44
     }^{(
    0.43
     unit
    0.43
     facility
    0.43
    Activations Density 0.066%

    No Known Activations