© 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. 22-RES-MATRYOSHKA-DC
    7. 2902
    Prev
    Next
    INDEX
    Explanations

    sections of research papers that perform analyses

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     continúas
    -0.79
    abestanden
    -0.59
     qualidade
    -0.56
    цездатний
    -0.52
    σθαι
    -0.51
    parsedMessage
    -0.50
    évaluateur
    -0.49
    ństwo
    -0.49
     calidad
    -0.48
     chargés
    -0.47
    POSITIVE LOGITS
     NSCoder
    0.71
     sequencing
    0.66
     transcrip
    0.63
     whole
    0.62
    sequ
    0.61
     prote
    0.61
    Portale
    0.61
    GetMapping
    0.60
    whole
    0.60
     Sequencing
    0.59
    Activations Density 0.281%

    No Known Activations