© 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. 12542
    Prev
    Next
    INDEX
    Explanations

    references to specific computational systems and methodologies

    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
    Negative Logits
     Bowie
    -0.73
    abetes
    -0.72
     Borno
    -0.69
     viejos
    -0.66
     Las
    -0.60
    âce
    -0.59
    Las
    -0.59
     Marav
    -0.58
     compliqué
    -0.57
    <h6>
    -0.57
    POSITIVE LOGITS
     Cent
    1.56
    Cent
    1.54
     CENT
    1.44
     cent
    1.39
     Centennial
    1.33
     Centurion
    1.27
    cent
    1.23
     Cents
    1.20
     centrifug
    1.18
     centroid
    1.17
    Activations Density 0.014%

    No Known Activations