© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9168
    Prev
    Next
    INDEX
    Explanations

    repeated elements or phrases, particularly related to licensing and compliance information

    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
    Negative Logits
    حمد
    -0.45
     legion
    -0.43
    chádz
    -0.42
     hingegen
    -0.42
    κολου
    -0.42
     invece
    -0.41
     withal
    -0.41
    Sonstiges
    -0.40
    ского
    -0.39
    Syn
    -0.39
    POSITIVE LOGITS
    NameInMap
    0.89
     تضيفلها
    0.87
    Портал
    0.82
    Tembelea
    0.82
     kaynağından
    0.82
    findpost
    0.79
    المناصب
    0.77
    VersionUID
    0.75
    Rüyada
    0.73
    Παραπομπές
    0.72
    Activations Density 0.005%

    No Known Activations