© 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. 7351
    Prev
    Next
    INDEX
    Explanations

    provisions that set forth guidelines or instructions

    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
    cendental
    -0.55
    meester
    -0.54
    !*\
    -0.53
    ']>
    -0.53
    ariable
    -0.52
     rebaj
    -0.52
    htdocs
    -0.52
     pican
    -0.52
     Lough
    -0.52
    POSITIVE LOGITS
     forth
    3.36
    forth
    2.13
     Forth
    2.06
    Forth
    1.85
     forward
    0.89
     fourth
    0.86
     Forward
    0.84
     вперед
    0.82
     adelante
    0.80
    fourth
    0.79
    Activations Density 0.007%

    No Known Activations