© 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. 26416
    Prev
    Next
    INDEX
    Explanations

    technical issues related to software bugs and their resolution

    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
     intptr
    -0.79
    enment
    -0.62
    脚注の使い方
    -0.60
    expandindo
    -0.56
    apeake
    -0.56
    quias
    -0.56
    portál
    -0.54
    ichier
    -0.54
     发表于
    -0.52
    chitis
    -0.52
    POSITIVE LOGITS
    AnimationsModule
    0.58
     vaccinated
    0.49
     BnF
    0.48
    glTranslatef
    0.47
    defect
    0.46
    mpto
    0.45
     najlepiej
    0.45
    objPHPExcel
    0.45
    NECTION
    0.45
    repe
    0.44
    Activations Density 0.094%

    No Known Activations