© 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. 12-RES-MATRYOSHKA-DC
    7. 26681
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to error analysis and fitting criteria in statistical modeling

    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
    CodeAttribute
    -0.52
    AddTagHelper
    -0.47
     perry
    -0.46
    çal
    -0.42
    客様
    -0.40
    Bert
    -0.39
     sign
    -0.38
     motor
    -0.38
    bert
    -0.36
     presen
    -0.36
    POSITIVE LOGITS
    PerformLayout
    0.75
     ostavi
    0.67
    medriver
    0.66
     pleaſure
    0.64
    AddField
    0.64
    瘩
    0.63
     purpoſe
    0.62
    LayoutPanel
    0.61
    ChildIndex
    0.61
     Divulgação
    0.60
    Activations Density 0.200%

    No Known Activations