© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 361
    Prev
    Next
    INDEX
    Explanations

    phrases introducing assumptions or conditions in mathematical or logical expressions

    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
    batore
    -0.88
    AndEndTag
    -0.83
    охра
    -0.82
     مشين
    -0.78
    findpost
    -0.76
    XMLSchema
    -0.73
     sphinx
    -0.73
    AxisSize
    -0.71
     محفوظة
    -0.71
     traseiro
    -0.71
    POSITIVE LOGITS
     Let
    1.13
    Let
    1.12
    let
    1.05
     LET
    1.05
     let
    0.99
    LET
    0.91
    lets
    0.83
     lets
    0.75
     Lett
    0.75
    Lets
    0.74
    Activations Density 0.425%

    No Known Activations