© 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. 22491
    Prev
    Next
    INDEX
    Explanations

    comparative phrases emphasizing significance or quantity

    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
    Not in Any Lists

    No Comments

    Negative Logits
    躇
    -0.61
     fometimes
    -0.60
    loit
    -0.54
    algunos
    -0.54
    otras
    -0.54
     portuguesa
    -0.52
    GetError
    -0.52
     Karsten
    -0.51
     Katowice
    -0.51
    leurs
    -0.50
    POSITIVE LOGITS
    enumi
    0.99
    sizeCache
    0.94
     مشين
    0.90
    GEBURTSDATUM
    0.87
    enumii
    0.80
    Tikang
    0.79
    ::_('
    0.79
     defaultstate
    0.75
     estekak
    0.74
    protoimpl
    0.73
    Activations Density 0.017%

    No Known Activations