© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1211
    Prev
    Next
    INDEX
    Explanations

    technical terms and software related to statistical analysis and data processing

    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
     EconPapers
    -0.82
     оригіналу
    -0.77
    SourceChecksum
    -0.77
    ^(@)
    -0.74
     &___
    -0.72
    SpringBootTest
    -0.70
    WebElementEntity
    -0.68
    WebVitals
    -0.67
     initComponents
    -0.66
     tartalomajánló
    -0.66
    POSITIVE LOGITS
     built
    0.49
    EndTag
    0.46
     online
    0.45
     estação
    0.44
     software
    0.43
     smtplib
    0.43
     rocz
    0.43
     variable
    0.42
    Released
    0.42
     V
    0.42
    Activations Density 0.499%

    No Known Activations