© 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. 23562
    Prev
    Next
    INDEX
    Explanations

    references to conventional methods or approaches

    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
     regola
    -0.68
    licazione
    -0.66
    I
    -0.65
    lus
    -0.65
     Albans
    -0.65
    </i>
    -0.63
    ares
    -0.63
     päiv
    -0.62
    zu
    -0.60
     ожи
    -0.59
    POSITIVE LOGITS
    WithIOException
    0.98
     Efq
    0.91
     estekak
    0.90
     GIPHY
    0.87
    featureID
    0.86
    SharedCtor
    0.81
    Conventional
    0.80
     Monfieur
    0.80
     myſelf
    0.80
    Wheeler
    0.79
    Activations Density 0.007%

    No Known Activations