© 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. 7588
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name, especially related to Al Mandoos

    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
    Hochspringen
    -0.74
    ReusableCell
    -0.74
     Jü
    -0.69
    thoven
    -0.65
    +#+
    -0.65
    AndroidJUnit
    -0.63
    TResult
    -0.63
    Amicalement
    -0.62
    ToScroll
    -0.61
    cinhas
    -0.60
    POSITIVE LOGITS
     Al
    2.84
    Al
    2.59
     AL
    1.76
     al
    1.32
     Аль
    1.30
    アル
    1.30
     Ал
    1.26
     Aluminum
    1.25
     aluminum
    1.24
     Alm
    1.23
    Activations Density 0.059%

    No Known Activations