© 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. 16185
    Prev
    Next
    INDEX
    Explanations

    tree

    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
     tree
    -0.94
     trees
    -0.92
    Tree
    -0.89
     Tree
    -0.84
    tree
    -0.84
     Trees
    -0.77
    Trees
    -0.73
    trees
    -0.73
     TREE
    -0.73
     समीक्षाओं
    -0.65
    POSITIVE LOGITS
    ArgsConstructor
    0.87
     BoxDecoration
    0.65
     organza
    0.60
     Proving
    0.59
     InputDecoration
    0.57
     Pharmacology
    0.56
     calorimeter
    0.56
    SourceChecksum
    0.56
    uws
    0.56
    }")
    0.55
    Activations Density 0.216%

    No Known Activations