© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90969
    Prev
    Next
    INDEX
    Explanations

    administration

    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
    Negative Logits
    ⓧ
    -0.75
    enterOuterAlt
    -0.66
     useDispatch
    -0.64
     ProtoMessage
    -0.63
    ChildScrollView
    -0.63
    SequentialGroup
    -0.61
     ModelExpression
    -0.61
    exitRule
    -0.61
     CURIAM
    -0.60
     isInitialized
    -0.59
    POSITIVE LOGITS
     BETWEEN
    0.51
     little
    0.49
     atleast
    0.49
     Between
    0.45
     light
    0.45
    curo
    0.44
     eight
    0.44
    ่ง
    0.44
     more
    0.44
     solid
    0.44
    Activations Density 0.001%

    No Known Activations