© 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. 1-RES-MATRYOSHKA-DC
    7. 1327
    Prev
    Next
    INDEX
    Explanations

    instances of performance evaluation or reference

    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
    ]")]
    -0.75
    InputBorder
    -0.72
    RenderAtEndOf
    -0.72
    省市镇
    -0.67
     виправивши
    -0.64
    UnifiedTopology
    -0.63
     ALC
    -0.62
    krok
    -0.61
    ManagedBean
    -0.61
    DockStyle
    -0.60
    POSITIVE LOGITS
     performance
    4.66
     Performance
    4.34
    Performance
    4.31
    performance
    4.19
     PERFORMANCE
    4.06
    PERFORMANCE
    3.72
     performances
    3.50
     Performances
    3.08
    Performances
    2.94
     desempenho
    2.66
    Activations Density 0.509%

    No Known Activations