© 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. 24-RES-MATRYOSHKA-DC
    7. 632
    Prev
    Next
    INDEX
    Explanations

    proper nouns, dates, and numerical information from historical documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    ंदीखरीदारी
    -0.68
     Heathrow
    -0.61
     randomised
    -0.60
     Behavioural
    -0.59
     behavioural
    -0.59
     privatisation
    -0.59
     motorway
    -0.57
    بوابة
    -0.57
    locaust
    -0.57
    Ещё
    -0.57
    POSITIVE LOGITS
     steamboat
    0.63
     Colored
    0.62
    //
    0.61
     temperance
    0.59
     colored
    0.58
     wagon
    0.57
    MessageOf
    0.56
    stus
    0.56
    Colored
    0.55
     MainAxisSize
    0.55
    Activations Density 1.498%

    No Known Activations