© 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. 15991
    Prev
    Next
    INDEX
    Explanations

    sequence patterns and structural representations in data, particularly related to molecular or genomic sequences

    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
    -0.85
     للاسماء
    -0.85
    nestjs
    -0.83
     ligiloj
    -0.82
     שוליים
    -0.81
    LookAnd
    -0.81
     <=",
    -0.81
     <>",
    -0.79
    WriteTagHelper
    -0.77
    :✨
    -0.76
    POSITIVE LOGITS
     geb
    0.45
     ouv
    0.40
    ც
    0.40
    setContentView
    0.40
    SPATH
    0.40
    zels
    0.40
    「
    0.40
    mesine
    0.38
    ℏ
    0.38
    خلا
    0.38
    Activations Density 0.086%

    No Known Activations