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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15322
    Prev
    Next
    INDEX
    Explanations

    patterns related to code or configuration instructions in technical or programming text

    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
    脚注の使い方
    -1.05
     ddelweddau
    -1.02
    +#+#
    -0.98
    IntoConstraints
    -0.96
     CreateTagHelper
    -0.91
     تانيه
    -0.82
     nakalista
    -0.82
    MessageTagHelper
    -0.81
     فريبيس
    -0.79
     NSCoder
    -0.77
    POSITIVE LOGITS
    MOD
    1.31
    COL
    1.10
     COL
    1.10
     MOD
    0.94
    MET
    0.89
     MET
    0.79
     MED
    0.76
     MIL
    0.75
    MED
    0.72
    MIL
    0.69
    Activations Density 0.003%

    No Known Activations