© 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. 12507
    Prev
    Next
    INDEX
    Explanations

    references to businesses or firms

    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
     amb
    -0.66
     HUN
    -0.65
    apas
    -0.61
     Caron
    -0.60
    titus
    -0.59
    ELEM
    -0.57
    </b>
    -0.57
     fac
    -0.57
    qués
    -0.57
    ش
    -0.57
    POSITIVE LOGITS
     Firms
    1.88
     Firm
    1.77
    Firm
    1.75
    firm
    1.72
     firms
    1.70
     FIRM
    1.61
     firm
    1.52
    Fir
    1.38
     firme
    1.29
     FIR
    1.22
    Activations Density 0.008%

    No Known Activations