© 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. 1-RES-MATRYOSHKA-DC
    7. 626
    Prev
    Next
    INDEX
    Explanations

    references to laboratory procedures involving sample preparation, processing, and chemical reactions

    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
    ↵
    -0.56
     I
    -0.50
     (
    -0.49
    <eos>
    -0.45
    ,
    -0.45
     and
    -0.45
     M
    -0.44
     en
    -0.43
     "
    -0.43
     di
    -0.42
    POSITIVE LOGITS
     itſelf
    1.27
     myſelf
    1.23
     doubtnut
    1.20
     Efq
    1.13
     Monfieur
    1.09
     himſelf
    1.07
     ―――――
    1.07
     Administrativna
    1.05
     ſeveral
    1.05
     houſe
    1.05
    Activations Density 5.737%

    No Known Activations