© 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. 5777
    Prev
    Next
    INDEX
    Explanations

    references to the initial point or beginning of a process or sequence

    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
     فريبيس
    -1.02
     ISNI
    -0.84
    存于互联网档案馆
    -0.73
     ProtoMessage
    -0.69
     onCreateView
    -0.67
     autorytatywna
    -0.65
    Попис
    -0.64
    ukunft
    -0.63
     andata
    -0.63
    reportWebVitals
    -0.62
    POSITIVE LOGITS
     initially
    0.62
     originally
    0.56
    Initially
    0.56
    Originally
    0.55
     Laufe
    0.54
     Initially
    0.53
    izer
    0.51
    vierno
    0.50
     ujednoznacz
    0.49
     сча
    0.48
    Activations Density 0.107%

    No Known Activations