© 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. 26943
    Prev
    Next
    INDEX
    Explanations

    terms related to duplication and redundancy

    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
    PMailer
    -0.83
    OkHttpClient
    -0.82
     ESM
    -0.79
    SourceChecksum
    -0.78
     Sita
    -0.77
     Nj
    -0.76
    gdx
    -0.75
    DotNetBar
    -0.74
     }:
    -0.73
    '].'
    -0.73
    POSITIVE LOGITS
     Dup
    1.09
    Dup
    1.06
     dup
    1.00
     duplication
    0.84
    Duplicate
    0.81
     Dupont
    0.80
    duplicates
    0.78
    dup
    0.75
    Duplicates
    0.75
     Duplicate
    0.74
    Activations Density 0.008%

    No Known Activations