© 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. 23601
    Prev
    Next
    INDEX
    Explanations

    references to academic titles and names, particularly in the context of a professional setting

    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
     Lesen
    -0.52
    éte
    -0.49
     ไ
    -0.48
    益
    -0.48
    bedür
    -0.47
    wdata
    -0.46
     gouver
    -0.46
    pheny
    -0.46
    وح
    -0.45
     Sistema
    -0.45
    POSITIVE LOGITS
    djangoproject
    0.93
    ThroughAttribute
    0.91
    +#+
    0.89
    WaitGroup
    0.87
    HasForeignKey
    0.85
    TemporalType
    0.85
    下载附件
    0.84
    XmlAccessType
    0.84
    +#+#
    0.83
     nakalista
    0.82
    Activations Density 0.012%

    No Known Activations