© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events, particularly those involving dates and events from the United States

    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
    èdia
    -0.91
    rungsseite
    -0.90
    .*")]
    -0.88
     pinulongan
    -0.86
    Controllo
    -0.84
     contextLoads
    -0.81
     lenker
    -0.77
    djangoproject
    -0.76
    PerformLayout
    -0.74
    новниш
    -0.74
    POSITIVE LOGITS
    щиков
    0.44
     techo
    0.42
     Hel
    0.42
    ヘル
    0.40
     F
    0.40
     (
    0.40
     ($("#
    0.40
     вещей
    0.39
     Ho
    0.39
     Its
    0.38
    Activations Density 0.269%

    No Known Activations