© 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. 10765
    Prev
    Next
    INDEX
    Explanations

    functionality related to object or array manipulation in programming

    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
    <eos>
    -0.47
    放
    -0.46
    </h1>
    -0.45
    &
    -0.45
    ])[
    -0.44
    ,
    -0.42
     a
    -0.41
    tem
    -0.41
     :
    -0.41
    __
    -0.41
    POSITIVE LOGITS
    Datuak
    0.93
    zzleHttp
    0.93
     consultato
    0.93
     betweenstory
    0.91
     فريبيس
    0.90
     صوتيه
    0.88
    原始内容存档于
    0.84
     للمعارف
    0.83
    enumii
    0.83
    PostExecute
    0.82
    Activations Density 0.047%

    No Known Activations