© 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. 22278
    Prev
    Next
    INDEX
    Explanations

    references to scientific figures and their associated data points

    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
    BeginInit
    -0.57
    izer
    -0.49
    EndInit
    -0.48
     réussite
    -0.47
    .
    -0.45
    SourceChecksum
    -0.45
    InSection
    -0.44
     насеље
    -0.43
    _
    -0.43
    raj
    -0.43
    POSITIVE LOGITS
    expandindo
    0.73
    ="@+
    0.72
     ivelany
    0.62
    buntu
    0.62
    ANES
    0.62
    ancers
    0.61
    ^(@)
    0.60
     autorytatywna
    0.59
    ValueStyle
    0.58
    iconductor
    0.58
    Activations Density 0.071%

    No Known Activations