© 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. 28685
    Prev
    Next
    INDEX
    Explanations

    terms related to associations or connections between concepts

    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
     AppCompatTheme
    -0.69
    BagConstraints
    -0.63
     Roskov
    -0.61
    :✨
    -0.60
    avoit
    -0.58
     ogóle
    -0.56
     couch
    -0.56
     NTS
    -0.56
     VOR
    -0.54
    eurovision
    -0.54
    POSITIVE LOGITS
    TargetException
    0.74
    Carriera
    0.67
    setViewportView
    0.60
    ClientSize
    0.60
    ModelAdmin
    0.59
    tagHelperRunner
    0.58
    forName
    0.58
    cerned
    0.57
    =$?
    0.57
    numerusform
    0.55
    Activations Density 0.054%

    No Known Activations