© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26013
    Prev
    Next
    INDEX
    Explanations

    references to the world in a superlative context, such as "world's best" or "world's largest."

    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
    ViewInit
    -0.59
    Xna
    -0.59
    InSection
    -0.57
     programmatic
    -0.55
     חיצוניים
    -0.54
    oprot
    -0.52
     Quelles
    -0.51
    UnsafeEnabled
    -0.50
     Bohn
    -0.49
    richTextPanel
    -0.49
    POSITIVE LOGITS
     surla
    0.75
    %)$
    0.68
    %"),
    0.66
    __":
    0.64
    étricas
    0.64
    .'</
    0.63
    ."</
    0.62
    )))
    0.62
    AllAfrica
    0.59
    readFileSync
    0.59
    Activations Density 0.015%

    No Known Activations