© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 647
    Prev
    Next
    INDEX
    Explanations

    responses or alternatives

    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
    人都
    -0.63
    InjectAttribute
    -0.58
     pretty
    -0.57
     évidemment
    -0.55
     quite
    -0.53
     ovviamente
    -0.52
    SizeF
    -0.50
    лій
    -0.49
     pernah
    -0.48
     περί
    -0.48
    POSITIVE LOGITS
     instead
    4.25
    instead
    4.09
    Instead
    3.92
     Instead
    3.80
     rather
    3.64
    rather
    3.45
    Rather
    3.41
     Rather
    3.38
     plutôt
    2.95
     istället
    2.86
    Activations Density 0.319%

    No Known Activations