© 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. 8569
    Prev
    Next
    INDEX
    Explanations

    specific formatting or special characters

    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
    anyahu
    -0.88
     arşivlendi
    -0.86
    Christie
    -0.81
     SDLK
    -0.80
    (!__
    -0.79
     McNally
    -0.77
     linkovi
    -0.77
    FunctionFlags
    -0.77
     AssemblyTitle
    -0.77
     Hilde
    -0.77
    POSITIVE LOGITS
    °
    0.91
     Orrell
    0.69
    °°
    0.68
    tellung
    0.66
    ValueGeneration
    0.64
     ais
    0.64
     Armen
    0.64
    °)
    0.62
    ton
    0.61
    gang
    0.61
    Activations Density 0.000%

    No Known Activations