© 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. 717
    Prev
    Next
    INDEX
    Explanations

    code snippets related to invariant assertions and abstracted memory addresses

    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
    AndEndTag
    -0.56
     crush
    -0.50
     Ames
    -0.49
    lib
    -0.49
     bety
    -0.48
     letteratura
    -0.48
     Timp
    -0.48
     Sosa
    -0.47
     Alg
    -0.47
     rosette
    -0.45
    POSITIVE LOGITS
     uintptr
    6.69
    uintptr
    1.56
    HtmlAttribute
    0.98
    RuleContext
    0.90
     intptr
    0.88
    +#+
    0.84
     فريبيس
    0.81
     BoxFit
    0.79
    новниш
    0.78
    endphp
    0.77
    Activations Density 0.911%

    No Known Activations