© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4562
    Prev
    Next
    INDEX
    Explanations

    hexadecimal byte sequences and specific hex codes

    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
     then
    -0.53
     anyone
    -0.50
    дравствуйте
    -0.48
     lại
    -0.48
    τής
    -0.48
     متعلقه
    -0.47
     siapa
    -0.46
     or
    -0.45
    ின்ற
    -0.45
     dauern
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.93
    AndEndTag
    0.90
    migrationBuilder
    0.79
    httphttps
    0.77
    LookAnd
    0.77
    AsUp
    0.77
    MethodManager
    0.77
    GTCX
    0.75
     nakalista
    0.72
     noDo
    0.72
    Activations Density 0.111%

    No Known Activations