© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13392
    Prev
    Next
    INDEX
    Explanations

    references to buffer-related technical parameters

    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
    -1.24
     Buf
    -1.20
     Bu
    -1.06
    buf
    -1.06
    Bu
    -1.02
    Buf
    -0.99
     Buff
    -0.98
    BUF
    -0.90
    RetentionPolicy
    -0.89
     BUFF
    -0.88
    POSITIVE LOGITS
    buffer
    1.73
    SourceChecksum
    0.65
    ürd
    0.53
     Meksiku
    0.52
    مئ
    0.51
     uska
    0.48
    astru
    0.48
    xhtml
    0.46
     Punt
    0.45
    Patterns
    0.44
    Activations Density 0.002%

    No Known Activations