© 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. 1-CLT-HP
    7. 8785
    Prev
    Next
    INDEX
    Explanations

    to

    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
     ComVisible
    -0.62
     AttributeSet
    -0.53
     étend
    -0.46
     skolan
    -0.44
     baixo
    -0.44
    省市镇
    -0.44
    __*/
    -0.43
    dasarkan
    -0.43
     lò
    -0.43
     deler
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     Efq
    0.70
     متعلقه
    0.70
     /\.(
    0.65
    .}~\
    0.64
    UDAD
    0.62
     myſelf
    0.62
     itſelf
    0.59
     extrinsic
    0.58
    AutoField
    0.57
    Activations Density 0.560%

    No Known Activations