© 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. 23641
    Prev
    Next
    INDEX
    Explanations

    terms related to decoding processes and methods

    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
     AssemblyCulture
    -0.82
    GenerationType
    -0.77
     nakalista
    -0.74
    Jeografia
    -0.70
     FormData
    -0.68
    uchtigkeit
    -0.67
     verbe
    -0.67
    :+:
    -0.66
     wußte
    -0.66
    Andrés
    -0.65
    POSITIVE LOGITS
     Decoder
    1.50
     decoder
    1.48
    Decoder
    1.44
     decoding
    1.38
    Decode
    1.35
    decoder
    1.34
     Decode
    1.28
     decode
    1.26
    decode
    1.20
     decoded
    1.20
    Activations Density 0.011%

    No Known Activations