© 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. 30492
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate sections or descriptions of content within a document

    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
    protoimpl
    -0.54
    χη
    -0.46
    Delimited
    -0.45
     forfait
    -0.45
    iction
    -0.44
     vícti
    -0.42
    quity
    -0.42
     Herm
    -0.42
     Squeeze
    -0.41
     Italij
    -0.40
    POSITIVE LOGITS
     defaultstate
    0.79
    TypedDataSet
    0.73
    CloseOperation
    0.73
    دانشنامهٔ
    0.71
    الحياه
    0.71
    Rüyada
    0.70
    Jegyzetek
    0.69
    Климат
    0.69
    TagMode
    0.69
     चीज़ों
    0.69
    Activations Density 0.008%

    No Known Activations