© 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. 14536
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and relationships between variables

    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
     صوتيه
    -0.53
     AssemblyCulture
    -0.52
     InputDecoration
    -0.52
     насеље
    -0.52
     fuertemente
    -0.48
    Билгалдахарш
    -0.46
    ISupport
    -0.45
    yarnpkg
    -0.44
    nonatomic
    -0.43
    dAtA
    -0.42
    POSITIVE LOGITS
    \{\\
    0.76
     itſelf
    0.75
    bewerken
    0.75
    InjectAttribute
    0.66
    ">—
    0.65
     whoſe
    0.65
     nakalista
    0.64
    dolu
    0.64
     myſelf
    0.63
     виправивши
    0.61
    Activations Density 0.075%

    No Known Activations