© 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. 14248
    Prev
    Next
    INDEX
    Explanations

    code structure elements related to function definitions and error expectations

    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
    .
    -0.56
    Pinch
    -0.52
     el
    -0.52
     Numerade
    -0.52
    GroupLayout
    -0.49
    fit
    -0.48
     le
    -0.48
    jo
    -0.47
     r
    -0.47
    dat
    -0.46
    POSITIVE LOGITS
    ^(@)
    0.96
     doubtnut
    0.93
     Majefty
    0.90
     itſelf
    0.88
     ་་
    0.84
     nakalista
    0.83
    ſelves
    0.81
    ſelf
    0.79
    XmlAccessType
    0.79
     photolibrary
    0.78
    Activations Density 0.093%

    No Known Activations