© 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. 6439
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasons and justifications, particularly in a legal or formal context

    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
    PYX
    -0.75
    بوابة
    -0.57
    جغرافيا
    -0.52
    готовка
    -0.50
    Kjelder
    -0.49
    Дереккөздер
    -0.49
    참고
    -0.48
    niająca
    -0.47
    ISSE
    -0.45
    erts
    -0.44
    POSITIVE LOGITS
     these
    1.09
     this
    1.06
     thefe
    0.86
     этого
    0.82
     این
    0.81
    these
    0.79
     этих
    0.78
     queste
    0.78
     diesen
    0.74
     těchto
    0.74
    Activations Density 1.180%

    No Known Activations