© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    SQL queries related to data retrieval and aggregation

    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
     CanadaChoose
    -0.71
    posedge
    -0.69
    UnsafeEnabled
    -0.68
    出版年
    -0.66
    DeleteBehavior
    -0.66
    kyou
    -0.60
    RegressionTest
    -0.58
     Scale
    -0.57
     scale
    -0.57
    :].
    -0.57
    POSITIVE LOGITS
    /**
    0.57
    `.`
    0.50
     halluc
    0.48
    incón
    0.43
    GEBURTSDATUM
    0.43
     Souha
    0.43
     Arxiv
    0.42
     plantain
    0.42
    QtGui
    0.42
     flares
    0.42
    Activations Density 0.210%

    No Known Activations