© 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. 22945
    Prev
    Next
    INDEX
    Explanations

    references to legal offenses or 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
     CURLOPT
    -0.60
    #__
    -0.58
    alamus
    -0.57
    AsUp
    -0.57
     المعيارى
    -0.56
     dep
    -0.55
     Loo
    -0.55
    󠁿
    -0.54
    ulex
    -0.52
    듈
    -0.52
    POSITIVE LOGITS
     offence
    1.05
     Offense
    1.05
     offences
    1.03
     offenses
    1.02
     offense
    0.94
     offend
    0.87
     offended
    0.85
     actionTypes
    0.85
    offensive
    0.82
     offensi
    0.80
    Activations Density 0.008%

    No Known Activations