© 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. 15367
    Prev
    Next
    INDEX
    Explanations

    numeric values and their relationships in data reporting

    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
     Мексичка
    -1.04
    httphttps
    -0.98
     Efq
    -0.98
    Datuak
    -0.98
     purpoſe
    -0.93
     useRouter
    -0.89
    ^(@)
    -0.88
     EconPapers
    -0.85
     nahilalakip
    -0.85
    ſelves
    -0.85
    POSITIVE LOGITS
    .
    0.79
    ,
    0.59
     and
    0.58
     (
    0.56
    ↵↵
    0.56
    ;
    0.54
     which
    0.49
    <eos>
    0.45
     in
    0.45
     whereas
    0.45
    Activations Density 0.128%

    No Known Activations