© 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. 969
    Prev
    Next
    INDEX
    Explanations

    references to shell commands or scripts, particularly variations of 'sh', 'bash', and 'shell'

    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
     Teo
    -0.58
    /*
    -0.56
     Lain
    -0.56
     Tomb
    -0.55
     Dac
    -0.55
    crombie
    -0.52
     Roadster
    -0.52
     Jae
    -0.52
    Gregor
    -0.51
     صوتيه
    -0.51
    POSITIVE LOGITS
     sh
    2.89
     SH
    2.81
    SH
    2.80
     Sh
    2.73
    Sh
    2.73
    sh
    2.67
    Sha
    1.87
     Sho
    1.86
    Sho
    1.86
     Sha
    1.85
    Activations Density 0.572%

    No Known Activations