© 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. 20-CLT-HP
    7. 71546
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    np_max-act-logits · 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
     Pringle
    -0.58
    DoubleQuotes
    -0.51
    atste
    -0.49
    ipro
    -0.48
    batore
    -0.48
     chiuso
    -0.46
     Escu
    -0.45
    emploi
    -0.45
    quelles
    -0.44
    Toole
    -0.44
    POSITIVE LOGITS
    __(/*!
    0.60
    awaiter
    0.60
    wood
    0.59
    httphttps
    0.57
     BorderRadius
    0.55
    っこう
    0.54
    :✨
    0.53
    teenth
    0.53
    uxxxx
    0.52
    WOOD
    0.51
    Activations Density 0.001%

    No Known Activations