© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12538
    Prev
    Next
    INDEX
    Explanations

    instances of separable substances or components

    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
     Carroll
    -0.57
     Brady
    -0.54
    ConstraintMaker
    -0.51
     piezoelectric
    -0.50
    Carroll
    -0.50
    Brady
    -0.48
     propOrder
    -0.48
     del
    -0.46
    newArrayList
    -0.46
    indexPath
    -0.45
    POSITIVE LOGITS
    DAC
    1.09
     DAC
    1.08
     exploratory
    1.04
     Explor
    1.02
     separable
    1.00
     Cain
    0.97
    WithIOException
    0.90
    dac
    0.88
     ISNI
    0.87
     ALP
    0.85
    Activations Density 0.014%

    No Known Activations