© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 248
    Prev
    Next
    INDEX
    Explanations

    context surrounding statistical analysis in scientific studies

    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.18.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.18.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
     will
    -0.65
     part
    -0.57
    方便
    -0.56
    cios
    -0.55
     potential
    -0.54
     or
    -0.53
     possible
    -0.51
     human
    -0.51
     /
    -0.50
     may
    -0.50
    POSITIVE LOGITS
     noticeably
    0.99
     nettement
    0.93
     snippetHide
    0.90
    significantly
    0.90
     strikingly
    0.89
    showed
    0.88
     appreciably
    0.88
    WebElementEntity
    0.87
     markedly
    0.84
     marginally
    0.83
    Activations Density 6.235%

    No Known Activations