© 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. 6-RES-MATRYOSHKA-DC
    7. 1226
    Prev
    Next
    INDEX
    Explanations

    references to code sections

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.89
    Personendaten
    -0.82
    foria
    -0.75
    abstractmethod
    -0.74
    Wut
    -0.73
     nahilalakip
    -0.73
    PickerController
    -0.71
     оригіналу
    -0.69
    Билгалдахарш
    -0.68
    PREFERRED
    -0.67
    POSITIVE LOGITS
     §
    1.77
    §
    1.48
     §§
    1.38
    {§
    1.16
     §.
    0.89
     (§
    0.73
    ="#
    0.72
     Pf
    0.71
     Section
    0.66
    :#
    0.65
    Activations Density 0.037%

    No Known Activations