© 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. 25624
    Prev
    Next
    INDEX
    Explanations

    a specific structure or format in the data, indicating it may be looking for numerical or tabular values

    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
    complexType
    -0.49
    ownika
    -0.48
     cedo
    -0.48
    MethodManager
    -0.48
    chluss
    -0.47
     bulunabilir
    -0.46
     Neu
    -0.45
     privately
    -0.44
     subito
    -0.44
     Lankan
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    1.03
    Gambas
    0.83
     تضيفلها
    0.81
    +#+
    0.78
    ImageContext
    0.72
     Мексичка
    0.71
     ddelweddau
    0.70
    SpringBootTest
    0.68
    Autoritní
    0.67
     ComVisible
    0.66
    Activations Density 0.048%

    No Known Activations