© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    the presence of periods at the end of sentences

    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
    makeConstraints
    -0.85
     Fod
    -0.74
    й
    -0.74
     Prow
    -0.74
    hedral
    -0.72
    abetes
    -0.69
     Sarg
    -0.69
    imag
    -0.69
    ttemberg
    -0.68
    Poul
    -0.68
    POSITIVE LOGITS
    .\
    1.29
    ).\
    1.12
    }.\
    1.10
     .\
    0.90
    AsUp
    0.86
     onPage
    0.84
     незавершена
    0.83
     Dumont
    0.82
    Бахар
    0.79
     propOrder
    0.76
    Activations Density 0.014%

    No Known Activations