© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    phrases related to legitimacy and legal implications

    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
    енча
    -0.71
    duled
    -0.64
    ciless
    -0.64
    zegor
    -0.63
     BoxFit
    -0.63
    bourhood
    -0.61
    spaceBetween
    -0.61
    IZABETH
    -0.60
    ochlor
    -0.60
    mallow
    -0.60
    POSITIVE LOGITS
    Skocz
    0.66
    </em>
    0.63
     StatefulWidget
    0.58
    #![
    0.57
    fhir
    0.55
     Storms
    0.54
    杵
    0.54
    MathML
    0.53
    ko
    0.52
    chdir
    0.52
    Activations Density 0.010%

    No Known Activations