© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5430
    Prev
    Next
    INDEX
    Explanations

    of

    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
     quoi
    -0.49
    tamment
    -0.46
    RenderAtEndOf
    -0.45
     maupun
    -0.44
     novedad
    -0.44
    openzeppelin
    -0.44
     idag
    -0.43
     utanför
    -0.43
     compris
    -0.43
     realizzata
    -0.43
    POSITIVE LOGITS
     all
    1.08
     most
    0.81
     much
    0.76
     almost
    0.69
     many
    0.67
     ALL
    0.64
     nearly
    0.63
     tất
    0.63
    ArgsConstructor
    0.63
     key
    0.62
    Activations Density 0.003%

    No Known Activations