© 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. 4-CLT-HP
    7. 383
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    AxisAlignment
    -0.71
    awtextra
    -0.70
    WebVitals
    -0.62
     useCallback
    -0.62
    tvguidetime
    -0.61
    NameInMap
    -0.58
     références
    -0.57
    msgTypes
    -0.57
    ◄
    -0.56
     useParams
    -0.56
    POSITIVE LOGITS
     the
    1.05
     our
    0.67
     hands
    0.60
     educators
    0.59
     tackling
    0.57
     Hände
    0.57
     professores
    0.56
    hands
    0.55
     physicians
    0.55
     Hands
    0.55
    Activations Density 0.006%

    No Known Activations