© 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. 22724
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific reports and investigations, particularly concerns about contamination and misidentification

    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
     участь
    -0.56
    ConstraintMaker
    -0.52
    ostomy
    -0.52
    WriteTagHelper
    -0.49
     участие
    -0.49
     bahay
    -0.47
     Orpheus
    -0.47
    enderror
    -0.46
    المناصب
    -0.46
    setViewName
    -0.46
    POSITIVE LOGITS
     noqa
    0.63
     Paglinawan
    0.53
     HasFactory
    0.52
     mencu
    0.50
     False
    0.50
     bParam
    0.50
    ADVERTISEMENT
    0.50
    ̀nh
    0.50
     المعيارى
    0.50
     convertView
    0.48
    Activations Density 0.174%

    No Known Activations