© 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. 12-RES-MATRYOSHKA-DC
    7. 5038
    Prev
    Next
    INDEX
    Explanations

    references to murder and related 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
    Personensuche
    -0.84
     armis
    -0.73
     Mares
    -0.72
     Aruba
    -0.68
     Paesi
    -0.66
     obicei
    -0.66
     distress
    -0.65
    Độ
    -0.64
     Applicant
    -0.62
     dzień
    -0.62
    POSITIVE LOGITS
     Murder
    1.27
    Murder
    1.18
     murder
    1.17
     murders
    1.12
    murder
    1.07
     murderers
    0.98
     Murders
    0.94
     murdered
    0.91
     MUR
    0.90
     murderer
    0.86
    Activations Density 0.046%

    No Known Activations