© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6616
    Prev
    Next
    INDEX
    Explanations

    references to legal rules, standards, and procedural concepts

    oai_token-act-pair · gpt-4.1-nano
    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
     Normdatei
    -1.27
     démocr
    -1.13
     Monfieur
    -1.13
    KommentareTeilen
    -1.09
    EDEFAULT
    -1.09
     Cæsar
    -1.06
     quæ
    -1.05
     Efq
    -1.04
     scolaires
    -1.03
    ########.
    -1.01
    POSITIVE LOGITS
     
    0.64
     multi
    0.47
    da
    0.45
     mis
    0.45
     se
    0.44
     str
    0.44
     non
    0.43
     bas
    0.43
     ne
    0.43
     so
    0.43
    Activations Density 0.996%

    No Known Activations