© 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. 12-RES-MATRYOSHKA-DC
    7. 20142
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating software package distribution paths

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idopsis
    -0.93
     Schenk
    -0.92
     utafitiHapana
    -0.92
    culosis
    -0.89
    Andrey
    -0.88
    ogeneous
    -0.88
    Tikang
    -0.86
     Gabel
    -0.85
     MRP
    -0.85
     GenerationType
    -0.84
    POSITIVE LOGITS
     Dist
    0.94
     dist
    0.87
    Dist
    0.83
    dist
    0.82
     distress
    0.82
     DIST
    0.81
     Tess
    0.80
     distortions
    0.79
     Distortion
    0.76
     distortion
    0.76
    Activations Density 0.025%

    No Known Activations