© 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. 20921
    Prev
    Next
    INDEX
    Explanations

    references to specific names and titles, particularly in the context of organizations and groups

    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
     CURIAM
    -0.73
    twimg
    -0.62
     שוליים
    -0.62
    DMETHOD
    -0.62
    хьтан
    -0.61
    Rohy
    -0.60
    Ikus
    -0.59
    argout
    -0.57
    Archite
    -0.56
    Билгалдахарш
    -0.55
    POSITIVE LOGITS
     Paglinawan
    0.67
    Numerology
    0.61
    Turned
    0.50
     industriales
    0.49
     tillbaka
    0.48
    Tetapi
    0.47
     withal
    0.46
    mtrl
    0.45
     متعلقه
    0.45
     normales
    0.44
    Activations Density 0.576%

    No Known Activations