© 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. 1-CLT-HP
    7. 9488
    Prev
    Next
    INDEX
    Explanations

    domain

    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
     ModelExpression
    -0.59
    ConstraintMaker
    -0.59
     CreateTagHelper
    -0.56
    OGND
    -0.55
    ̍t
    -0.55
     GetEnumerator
    -0.53
    DataMember
    -0.52
     OkHttpClient
    -0.50
     Vikipedi
    -0.47
    othelial
    -0.47
    POSITIVE LOGITS
     the
    0.60
     suggesting
    0.60
     that
    0.59
     bringing
    0.59
     classifying
    0.58
     selecting
    0.57
     a
    0.56
    UTELY
    0.56
     affording
    0.56
     tagging
    0.54
    Activations Density 0.049%

    No Known Activations