© 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. 15573
    Prev
    Next
    INDEX
    Explanations

    high numerical values in data related to measurements or thresholds

    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
     Theſe
    -1.05
     myſelf
    -1.00
    ſelf
    -0.98
     himſelf
    -0.97
     ſever
    -0.95
     themſelves
    -0.94
     poffible
    -0.93
     ſeveral
    -0.92
     ſhall
    -0.91
     pleaſure
    -0.91
    POSITIVE LOGITS
     kasarigan
    0.88
    migrationBuilder
    0.75
    Jereo
    0.73
    memoized
    0.67
    parsedMessage
    0.65
    figsize
    0.65
    squ
    0.64
    qtt
    0.62
    WithIOException
    0.61
    -------------</
    0.61
    Activations Density 0.016%

    No Known Activations