© 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. 22203
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
     ddelweddau
    -0.96
     الرياضيه
    -0.93
     onAnimation
    -0.86
     تضيفلها
    -0.69
     المعيارى
    -0.69
    CloseOperation
    -0.67
     שוליים
    -0.67
     للاسماء
    -0.66
    رشف
    -0.66
     мәкал
    -0.64
    POSITIVE LOGITS
    etine
    0.55
     simply
    0.54
    ята
    0.54
     habitudes
    0.54
     }],
    0.53
     Tenden
    0.53
     ever
    0.51
     fundamentales
    0.51
     mør
    0.51
    Tem
    0.49
    Activations Density 0.076%

    No Known Activations