© 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. 15891
    Prev
    Next
    INDEX
    Explanations

    code snippets or keywords associated with Django models

    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
    ngdoc
    -0.60
    contentLoaded
    -0.52
    esten
    -0.49
     AssemblyProduct
    -0.47
     gezin
    -0.47
    المناصب
    -0.46
     الحره
    -0.43
    WICK
    -0.43
     Tren
    -0.43
    ***********/
    -0.43
    POSITIVE LOGITS
    ModelAdmin
    0.93
     django
    0.88
    CharField
    0.76
    ThroughAttribute
    0.75
    djangoproject
    0.75
    queryset
    0.74
    SequentialGroup
    0.73
     useStyles
    0.72
    RUnlock
    0.71
     nakalista
    0.69
    Activations Density 0.015%

    No Known Activations