© 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. 224
    Prev
    Next
    INDEX
    Explanations

    still

    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
     still
    -0.66
    GraphicsUnit
    -0.60
    Huhu
    -0.59
    
    -0.59
     retaining
    -0.59
    stateProvider
    -0.55
    still
    -0.54
     retain
    -0.53
    readlines
    -0.53
     staying
    -0.53
    POSITIVE LOGITS
    SourceChecksum
    0.46
    χρι
    0.45
     and
    0.44
    ulturen
    0.44
    engeance
    0.44
     (/
    0.44
    Демографія
    0.44
    ItemBackground
    0.44
     bookId
    0.43
    /
    0.43
    Activations Density 0.004%

    No Known Activations