© 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. 27062
    Prev
    Next
    INDEX
    Explanations

    references to legal citations or documentation within a text

    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
     myſelf
    -1.00
    ^(@)
    -0.92
     doubtnut
    -0.88
     Monfieur
    -0.87
     Efq
    -0.85
    randomUUID
    -0.80
    Autoritní
    -0.79
    wiſe
    -0.79
     purpoſe
    -0.77
    []
    -0.77
    POSITIVE LOGITS
    <h4>
    0.69
     externes
    0.60
    mListener
    0.58
     //$
    0.57
    methe
    0.56
     مشين
    0.55
    ße
    0.54
    or
    0.53
    providedIn
    0.52
     molasses
    0.49
    Activations Density 0.034%

    No Known Activations