© 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. 23736
    Prev
    Next
    INDEX
    Explanations

    terms related to health, biology, and physical systems

    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
     itſelf
    -0.77
     للمعارف
    -0.77
     myſelf
    -0.75
    tvguidetime
    -0.71
    ſelves
    -0.71
     themſelves
    -0.71
     pleaſure
    -0.69
     raiſ
    -0.68
    +#+#
    -0.68
    IndentedString
    -0.67
    POSITIVE LOGITS
     
    0.62
    .
    0.59
     the
    0.57
    oneof
    0.55
     kér
    0.49
    ↵↵↵
    0.49
    ↵↵
    0.49
    .,
    0.48
     asistencia
    0.48
     именно
    0.47
    Activations Density 0.343%

    No Known Activations