© 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. 92666
    Prev
    Next
    INDEX
    Explanations

    Attribution using "by"

    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
    BagConstraints
    -0.69
    DockStyle
    -0.66
     Itself
    -0.62
    AttributeSet
    -0.61
     JpaRepository
    -0.59
    richTextPanel
    -0.58
    AlterField
    -0.56
     Roskov
    -0.54
    новништво
    -0.54
    ">—
    -0.54
    POSITIVE LOGITS
     most
    0.77
     classmates
    0.71
     society
    0.65
     fellow
    0.61
     rekan
    0.57
     other
    0.56
     many
    0.55
    tonode
    0.55
     family
    0.54
     friends
    0.53
    Activations Density 0.002%

    No Known Activations