© 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. 2-RES-MATRYOSHKA-DC
    7. 6324
    Prev
    Next
    INDEX
    Explanations

    references to automatic or default code transformations

    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
    ScopeManager
    -0.75
     дописавши
    -0.73
    MENAFN
    -0.72
     NSCoder
    -0.69
    }],
    -0.68
    styleType
    -0.65
     endwhile
    -0.65
    AutoField
    -0.61
     ""],
    -0.60
    )}_{
    -0.59
    POSITIVE LOGITS
     Polda
    0.67
     functor
    0.55
     censiti
    0.55
    leroi
    0.54
     mainland
    0.53
     rayo
    0.52
     plainte
    0.49
    lanze
    0.48
    étranger
    0.48
    nobyl
    0.48
    Activations Density 1.331%

    No Known Activations