© 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. 3983
    Prev
    Next
    INDEX
    Explanations

    references to specific technical components and parameter names related to graph or data structure implementations

    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
     MainAxisSize
    -0.75
    tagHelperRunner
    -0.74
     itſelf
    -0.73
     intptr
    -0.71
     tartalomajánló
    -0.68
    uxxxx
    -0.66
    ")));
    -0.65
    Portail
    -0.63
    TagHelper
    -0.63
    XmlAccessType
    -0.63
    POSITIVE LOGITS
    usercontent
    0.56
    netbeans
    0.55
    ForType
    0.54
    ResumeLayout
    0.52
    にして
    0.49
    Архівовано
    0.49
     đó
    0.48
     ['./
    0.47
    afone
    0.45
    EndContext
    0.45
    Activations Density 1.406%

    No Known Activations