© 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. 17333
    Prev
    Next
    INDEX
    Explanations

    structures related to code syntax and functions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rome
    -0.62
    fromCharCode
    -0.60
    zige
    -0.59
    telefono
    -0.58
    miştir
    -0.58
    DIRS
    -0.54
    Joanne
    -0.53
    (__('
    -0.51
     Joanne
    -0.48
    haer
    -0.48
    POSITIVE LOGITS
     Roskov
    1.05
    oredCriteria
    1.05
    principalTable
    0.98
    tagHelperRunner
    0.98
    fromnode
    0.88
     myſelf
    0.83
    enumi
    0.82
    تقاوى
    0.81
    ViewFeatures
    0.80
     }}"></
    0.80
    Activations Density 0.073%

    No Known Activations