© 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. 5340
    Prev
    Next
    INDEX
    Explanations

    mentions of a buffer variable or related buffer operations

    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
     buf
    -1.23
    buf
    -0.96
     Buf
    -0.81
     Schmitz
    -0.77
    CppMethod
    -0.74
    Buf
    -0.74
    BUF
    -0.70
     Bu
    -0.69
    MENAFN
    -0.68
     bu
    -0.66
    POSITIVE LOGITS
    buffer
    0.93
     Reverso
    0.69
     disambiguazione
    0.66
     Marlin
    0.63
    BUFFER
    0.52
     Meksiku
    0.52
    AndEndTag
    0.52
     Arka
    0.51
    zeera
    0.50
    otient
    0.49
    Activations Density 0.008%

    No Known Activations