© 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. 30142
    Prev
    Next
    INDEX
    Explanations

    mathematical phrases involving replacements or substitutions within formal definitions or proofs

    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
     rest
    -0.55
     hưởng
    -0.51
    ItemBackground
    -0.50
     practice
    -0.50
     resto
    -0.49
    таратура
    -0.49
    lihood
    -0.47
    raft
    -0.46
    Nationalité
    -0.46
     beque
    -0.46
    POSITIVE LOGITS
     snippetHide
    0.81
     صوتيه
    0.72
     consultato
    0.71
     détru
    0.68
     esternos
    0.65
     ferons
    0.64
     venons
    0.64
     découver
    0.61
     écout
    0.60
     fermée
    0.60
    Activations Density 0.044%

    No Known Activations