© 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. 25927
    Prev
    Next
    INDEX
    Explanations

    phrases expressing implications, challenges, and roles in various 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
    \{\\
    -0.79
    ]='\
    -0.76
    AnimationsModule
    -0.75
     ExecuteAsync
    -0.71
     noDo
    -0.70
     itſelf
    -0.69
    NUMX
    -0.68
     typelib
    -0.68
    XmlAccessorType
    -0.67
     ostavi
    -0.67
    POSITIVE LOGITS
    antd
    0.53
    tagHelperRunner
    0.51
     ameste
    0.48
    expect
    0.46
    :
    0.45
     serez
    0.42
    AndUpdate
    0.42
    ,
    0.42
    pov
    0.41
    Gizmos
    0.41
    Activations Density 0.510%

    No Known Activations