© 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. 11639
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or structures

    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
     évêque
    -0.72
     paroisse
    -0.64
     vermelhas
    -0.63
     dégâts
    -0.63
    Bibliographie
    -0.61
     fusca
    -0.60
    isip
    -0.60
     dinos
    -0.60
     brancas
    -0.60
    PositiveButton
    -0.60
    POSITIVE LOGITS
    IndentedString
    0.67
    mphony
    0.66
    CloseOperation
    0.66
    ctional
    0.63
    izr
    0.63
    expandindo
    0.62
    bewerken
    0.62
    RegistryLite
    0.62
    ."<
    0.60
     Under
    0.60
    Activations Density 0.011%

    No Known Activations