© 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. 22-RES-MATRYOSHKA-DC
    7. 2915
    Prev
    Next
    INDEX
    Explanations

    the word "sample" and related terms, especially in research or statistical contexts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    StoryboardSegue
    -0.56
    ally
    -0.52
    ArgsConstructor
    -0.50
     bâton
    -0.49
    Aiheesta
    -0.49
    ParallelGroup
    -0.48
     sép
    -0.47
     CGFloat
    -0.47
    zarchiwizowane
    -0.47
    ViewInit
    -0.47
    POSITIVE LOGITS
     Samples
    1.36
    samples
    1.27
     samples
    1.27
    Samples
    1.22
     SAMPLE
    1.02
     SAMPLES
    1.01
    SAMPLE
    1.00
    SAMPLES
    0.99
     Sample
    0.96
     Proben
    0.90
    Activations Density 0.199%

    No Known Activations