© 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. 25825
    Prev
    Next
    INDEX
    Explanations

    references to academic journals

    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
    ########.
    -0.80
    ViewFeatures
    -0.70
     }^{(
    -0.69
    efte
    -0.66
     Ricky
    -0.66
    }}^{(
    -0.65
    /-/
    -0.63
     Sira
    -0.63
    xiu
    -0.63
    onAttach
    -0.61
    POSITIVE LOGITS
     Journals
    1.22
     Journal
    1.13
     journal
    1.11
     journals
    1.07
    nment
    1.06
    Journal
    1.05
     JOURNAL
    1.05
    JOURNAL
    0.99
    Jour
    0.98
    journal
    0.97
    Activations Density 0.007%

    No Known Activations