© 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. 12-RES-MATRYOSHKA-DC
    7. 9504
    Prev
    Next
    INDEX
    Explanations

    terms related to boundary conditions and periodic systems in mathematical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    arg
    -0.48
    artment
    -0.45
    mino
    -0.45
    gande
    -0.45
     zawier
    -0.43
    Deleting
    -0.43
     sayap
    -0.42
    SAB
    -0.41
    Hulk
    -0.41
    utters
    -0.41
    POSITIVE LOGITS
    mergeFrom
    0.86
     Roskov
    0.71
    SharedDtor
    0.71
    principalColumn
    0.70
    EndGlobalSection
    0.69
    kloped
    0.68
    StoreMessageInfo
    0.66
     referrerpolicy
    0.65
     חיצוניים
    0.64
    )))));
    0.63
    Activations Density 0.046%

    No Known Activations