© 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. 11670
    Prev
    Next
    INDEX
    Explanations

    references to types and structures commonly used in programming, particularly around updates and data management

    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
    AnchorStyles
    -0.99
    脚注の使い方
    -0.90
    IsContent
    -0.88
    RepeatedField
    -0.88
     pulumi
    -0.84
    IsMutable
    -0.79
    
    -0.79
    󠁢
    -0.77
    InjectAttribute
    -0.76
    fjspx
    -0.76
    POSITIVE LOGITS
    endpush
    0.56
     one
    0.48
     man
    0.45
    TestBed
    0.45
     model
    0.45
     over
    0.45
    -
    0.45
     Ko
    0.43
    :=\
    0.42
     died
    0.42
    Activations Density 0.002%

    No Known Activations