© 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. 23059
    Prev
    Next
    INDEX
    Explanations

    references to naming conflicts and variable naming conventions in code

    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
     مشين
    -0.76
    lably
    -0.68
     lenker
    -0.63
     engraçadas
    -0.63
     autorytatywna
    -0.62
     aikaa
    -0.62
     Añade
    -0.61
    SerializedSize
    -0.60
    findpost
    -0.59
     nyingi
    -0.59
    POSITIVE LOGITS
     postIndex
    0.47
     posed
    0.45
    úd
    0.43
     existing
    0.42
    Vesti
    0.42
    χυ
    0.42
     furn
    0.41
     matching
    0.41
     Chem
    0.41
     Optics
    0.41
    Activations Density 0.074%

    No Known Activations