© 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. 0-RES-MATRYOSHKA-DC
    7. 10763
    Prev
    Next
    INDEX
    Explanations

    references to database entries, identifiers, or structured data references

    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
    Not in Any Lists

    No Comments

    Negative Logits
    âmetros
    -0.58
    rettet
    -0.55
    Бахар
    -0.54
    PerformLayout
    -0.52
    ṁ
    -0.51
    \|^{
    -0.49
    ichthys
    -0.49
    AutoScale
    -0.49
    lamiento
    -0.47
     tanya
    -0.47
    POSITIVE LOGITS
     diversification
    0.96
    pox
    0.90
    InjectAttribute
    0.89
     diversify
    0.82
     Mona
    0.80
     Brock
    0.80
     Rican
    0.79
     seas
    0.79
    Brock
    0.77
     jadx
    0.77
    Activations Density 0.020%

    No Known Activations