© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16592
    Prev
    Next
    INDEX
    Explanations

    compliance-related terminology

    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
    లాలు
    -0.65
     αφ
    -0.59
     Himo
    -0.59
    ésult
    -0.57
     Uint
    -0.57
     createState
    -0.56
    vastava
    -0.56
    Kaynakça
    -0.55
     stdout
    -0.55
    ξω
    -0.55
    POSITIVE LOGITS
     doInBackground
    0.56
     sortant
    0.54
    Uninitialized
    0.51
    +:+
    0.50
    endphp
    0.49
     personnaliser
    0.49
     kaarangay
    0.49
     Biôgrafia
    0.48
     Nasional
    0.48
     both
    0.47
    Activations Density 0.044%

    No Known Activations