© 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. 17352
    Prev
    Next
    INDEX
    Explanations

    references to orders of magnitude in numerical data

    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
    assets
    -0.47
    绩
    -0.47
    xid
    -0.45
    ప
    -0.44
     Kalt
    -0.43
    content
    -0.43
    ctivo
    -0.43
     „
    -0.43
     عط
    -0.42
     Rewards
    -0.42
    POSITIVE LOGITS
     виправивши
    1.05
     tartalomajánló
    1.01
    IVEREF
    0.99
    DeleteBehavior
    0.95
    Geplaatst
    0.92
    Personendaten
    0.91
    writeField
    0.88
    SequentialGroup
    0.86
     Савезне
    0.86
    FormTagHelper
    0.84
    Activations Density 0.005%

    No Known Activations