© 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. 14985
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue

    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
     
    -0.57
    zval
    -0.47
    ↵
    -0.46
    ensical
    -0.44
    тится
    -0.43
     in
    -0.42
    companying
    -0.41
    bės
    -0.40
    bringt
    -0.40
    }}]{
    -0.40
    POSITIVE LOGITS
    XmlAccessorType
    0.84
     referenties
    0.81
    ⓧ
    0.81
    findpost
    0.79
    دانشنامهٔ
    0.77
    تقاوى
    0.75
    tvguidetime
    0.75
    InitVars
    0.74
    InjectAttribute
    0.73
     crystall
    0.71
    Activations Density 0.010%

    No Known Activations