© 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. 24-RES-MATRYOSHKA-DC
    7. 1250
    Prev
    Next
    INDEX
    Explanations

    numbers often related to measurements or quantities

    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.24.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.24.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
    :✨
    -0.66
     pinulongan
    -0.65
    تقاوى
    -0.60
    Portály
    -0.57
    PUR
    -0.57
     OMITBAD
    -0.56
    Према
    -0.52
    Viitteet
    -0.50
    eqref
    -0.50
     méri
    -0.49
    POSITIVE LOGITS
     thousands
    1.02
     thousand
    0.99
     Thousands
    0.92
     Thousand
    0.88
    Thousands
    0.87
    thousands
    0.87
    Thousand
    0.87
    thousand
    0.82
     THOUS
    0.81
     thous
    0.75
    Activations Density 1.082%

    No Known Activations