© 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. 20085
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
     محفوظة
    -1.14
    DockStyle
    -1.00
     linkovi
    -0.93
    paravant
    -0.85
    principalTable
    -0.81
     EconPapers
    -0.81
    saraba
    -0.80
    titleMargin
    -0.79
    onedDateTime
    -0.77
    DeleteMapping
    -0.77
    POSITIVE LOGITS
    ::_
    0.54
    ↵↵
    0.53
    <eos>
    0.52
     .
    0.50
    uffer
    0.47
    Butterfly
    0.47
    displays
    0.47
    ופ
    0.47
    uff
    0.47
    reet
    0.47
    Activations Density 0.013%

    No Known Activations