© 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. 8611
    Prev
    Next
    INDEX
    Explanations

    phrases indicating parts or portions related to a whole

    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
     entire
    -0.99
     whole
    -0.96
     entirety
    -0.96
    whole
    -0.92
     full
    -0.90
    COMPLETE
    -0.87
     Entire
    -0.85
     COMPLETE
    -0.85
     ENTIRE
    -0.84
     complete
    -0.84
    POSITIVE LOGITS
    ised
    0.62
    Viki
    0.61
    TextHelper
    0.59
    RetentionPolicy
    0.57
     Snackbar
    0.56
    izing
    0.55
     refrigerated
    0.52
     MTN
    0.51
     à
    0.51
    TV
    0.50
    Activations Density 0.030%

    No Known Activations