© 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. 2727
    Prev
    Next
    INDEX
    Explanations

    features related to spectral properties and statistical measures in scientific data

    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
    ParallelGroup
    -0.86
    WriteTagHelper
    -0.73
    pexpr
    -0.68
    fromnode
    -0.63
    ++]=
    -0.63
    >`;
    -0.62
    Encyklopedia
    -0.60
     mergeFrom
    -0.60
    }}=$
    -0.59
    новниш
    -0.58
    POSITIVE LOGITS
    투
    0.52
    IContainer
    0.49
    Juno
    0.48
    piram
    0.45
    inaison
    0.44
     custody
    0.44
     commen
    0.43
    urysty
    0.42
     thông
    0.42
    ScreenState
    0.42
    Activations Density 0.408%

    No Known Activations