© 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. 11771
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with codes or regions

    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
    Charg
    -0.69
     iParam
    -0.67
    chise
    -0.64
    ."</
    -0.64
     nakalista
    -0.63
     setLoading
    -0.61
    痹
    -0.61
     setShow
    -0.60
    linec
    -0.60
     setOpen
    -0.60
    POSITIVE LOGITS
    DotNetBar
    1.01
     Gilli
    0.72
    /*
    0.69
     înd
    0.69
    kadot
    0.67
     prácti
    0.65
    inthians
    0.65
     Fonda
    0.64
     Apostle
    0.63
    tiary
    0.62
    Activations Density 0.150%

    No Known Activations