© 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. 14925
    Prev
    Next
    INDEX
    Explanations

    mentions of directory paths or directory-related 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
    Portail
    -0.71
     pageable
    -0.68
    ValueStyle
    -0.67
    SharedCtor
    -0.66
     appartiennent
    -0.62
     possano
    -0.60
     credere
    -0.59
    feof
    -0.59
     chimique
    -0.58
    </tfoot>
    -0.58
    POSITIVE LOGITS
     dir
    3.05
     Dir
    1.59
     DIR
    1.08
     dirs
    0.87
     dirty
    0.84
     dirt
    0.66
     dich
    0.65
    dirty
    0.65
     euch
    0.59
     Ihnen
    0.58
    Activations Density 0.002%

    No Known Activations