© 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. 24275
    Prev
    Next
    INDEX
    Explanations

    terms related to committing or completing crimes

    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
     nakalista
    -0.85
     propOrder
    -0.81
    niająca
    -0.63
     Efq
    -0.63
     Viitattu
    -0.61
    AccessorTable
    -0.59
    Radar
    -0.58
     Biro
    -0.58
    asgi
    -0.57
    arynge
    -0.56
    POSITIVE LOGITS
     cometer
    0.77
     commit
    0.75
    commits
    0.74
     commits
    0.71
     Commit
    0.70
     COMMIT
    0.62
     Picchu
    0.60
     committing
    0.60
    ########.
    0.60
     Corbu
    0.59
    Activations Density 0.012%

    No Known Activations