© 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. 12013
    Prev
    Next
    INDEX
    Explanations

    the use of the word "let" in mathematical or formal 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
     LET
    -0.80
     let
    -0.75
    let
    -0.74
    LET
    -0.73
     Let
    -0.67
     lets
    -0.66
    lle
    -0.65
    UseVisualStyle
    -0.65
     الرياضيه
    -0.64
     letting
    -0.63
    POSITIVE LOGITS
    AnchorStyles
    0.73
     connexe
    0.67
    ContentAlignment
    0.60
     connexes
    0.58
    erschein
    0.57
    TypeDef
    0.56
     romantique
    0.54
     للاسماء
    0.54
     indisponible
    0.53
     Trost
    0.53
    Activations Density 0.021%

    No Known Activations