© 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. 2-RES-MATRYOSHKA-DC
    7. 2463
    Prev
    Next
    INDEX
    Explanations

    references to specific types of clips or ties, especially those involving clips on ties or similar fasteners

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    HostException
    -0.69
     Tompkins
    -0.63
    antMatchers
    -0.61
    gines
    -0.60
    WebRequest
    -0.60
    yargs
    -0.60
    pula
    -0.60
    ellent
    -0.57
    
    -0.57
    SQLiteDatabase
    -0.57
    POSITIVE LOGITS
     clip
    3.45
     clips
    3.28
     Clip
    3.22
     Clips
    2.97
    Clip
    2.89
    clip
    2.86
     CLIP
    2.69
    Clips
    2.63
    clips
    2.56
    CLIP
    2.39
    Activations Density 0.007%

    No Known Activations