© 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. 1912
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate special cases or specific conditions within mathematical contexts

    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
    AsUp
    -0.72
    ślę
    -0.69
    بوابة
    -0.66
    цезда
    -0.65
    XmlAccessType
    -0.62
    Explicación
    -0.59
     Савезне
    -0.59
    +#+
    -0.56
     protoimpl
    -0.56
     lenker
    -0.55
    POSITIVE LOGITS
     становника
    0.60
     경우
    0.51
     Cæsar
    0.50
     speciale
    0.49
     special
    0.48
    Special
    0.47
     operazioni
    0.46
    TemporalType
    0.46
    ISupport
    0.46
    special
    0.45
    Activations Density 1.142%

    No Known Activations