© 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. 6040
    Prev
    Next
    INDEX
    Explanations

    references to scientific literature

    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
    ref
    -1.05
     ref
    -0.95
    REF
    -0.88
     Reference
    -0.79
     REF
    -0.78
     REFERENCE
    -0.76
    refs
    -0.75
    reff
    -0.75
    Ref
    -0.74
     useRef
    -0.73
    POSITIVE LOGITS
    tagHelperRunner
    0.83
     مشين
    0.62
    GraphicsUnit
    0.60
    NameInMap
    0.55
    données
    0.51
     universale
    0.50
    spender
    0.49
    ImageContext
    0.49
    vician
    0.48
    lück
    0.47
    Activations Density 0.047%

    No Known Activations