© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92998
    Prev
    Next
    INDEX
    Explanations

    Medical scientific papers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     piece
    -1.16
     pieces
    -0.87
     PIECE
    -0.84
    piece
    -0.82
     pezzo
    -0.82
    Pieces
    -0.79
    Piece
    -0.77
     Piece
    -0.74
    ness
    -0.73
     Pieces
    -0.73
    POSITIVE LOGITS
     nahilalakip
    0.63
    elemField
    0.61
    AddTagHelper
    0.60
    MLLoader
    0.57
    ReusableCell
    0.56
    rrggbb
    0.56
     AttributeSet
    0.52
    cinogenicity
    0.51
    UrlResolution
    0.50
    rillation
    0.50
    Activations Density 1.362%

    No Known Activations