© 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. 5998
    Prev
    Next
    INDEX
    Explanations

    terms related to bits and their properties in data representation and processing

    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
    efined
    -1.05
    PerformLayout
    -1.04
    (;;)
    -1.02
    BagConstraints
    -0.95
     Italijanski
    -0.91
    fficients
    -0.90
    ",""
    -0.88
    addCriterion
    -0.87
    hematical
    -0.87
     bezeichneter
    -0.86
    POSITIVE LOGITS
     BIT
    1.48
    bit
    1.45
     Bit
    1.41
    Bit
    1.41
    Bits
    1.37
    BIT
    1.33
     bit
    1.31
     Bits
    1.30
     bits
    1.25
    bits
    1.13
    Activations Density 0.067%

    No Known Activations