© 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. 16180
    Prev
    Next
    INDEX
    Explanations

    Could not determine any pattern.opy

    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
    opies
    -0.88
    opy
    -0.62
    ']='
    -0.59
    sonaro
    -0.58
     uVar
    -0.58
    ējās
    -0.58
    {?>
    -0.58
     QtWidgets
    -0.56
    __':
    -0.55
    pherals
    -0.54
    POSITIVE LOGITS
    EndContext
    0.53
    ImageContext
    0.52
     imageNamed
    0.49
     araw
    0.46
     of
    0.45
     vant
    0.45
    neros
    0.43
     handelt
    0.43
     deployed
    0.43
    getWorld
    0.43
    Activations Density 0.014%

    No Known Activations