© 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. 26849
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rarity or conditional situations

    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
    principalColumn
    -0.60
    adpleegd
    -0.59
    ----</
    -0.59
    ValueStyle
    -0.58
    sizeCache
    -0.57
    رشف
    -0.56
    haikusbot
    -0.55
     StatefulWidget
    -0.54
    ➟
    -0.54
    Française
    -0.54
    POSITIVE LOGITS
    DoubleQuotes
    0.60
     faults
    0.59
    <>();
    0.56
    mishes
    0.56
    MessageTagHelper
    0.56
     grie
    0.55
     fault
    0.54
    LOAT
    0.54
     problems
    0.51
     خط
    0.50
    Activations Density 0.664%

    No Known Activations