© 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. 22895
    Prev
    Next
    INDEX
    Explanations

    entries related to structured data or numerical information in a formatted context

    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
     OnInit
    -0.68
     picado
    -0.68
     dreamstime
    -0.67
     sobra
    -0.65
    Искәрмәләр
    -0.63
    ="@+
    -0.61
    Ith
    -0.60
    PostBack
    -0.60
     Namur
    -0.60
     boli
    -0.59
    POSITIVE LOGITS
     tartalomajánló
    0.88
    createCanvas
    0.58
    inheritDoc
    0.57
     оригіналу
    0.55
    LookAnd
    0.52
    ssaint
    0.52
    bigsqcup
    0.52
    ValueStyle
    0.51
    </tr>
    0.51
    afone
    0.51
    Activations Density 0.027%

    No Known Activations