© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax

    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
    RetentionPolicy
    -0.79
     Cæsar
    -0.71
     Majefty
    -0.69
    ſelves
    -0.64
     Jefus
    -0.63
    tvguidetime
    -0.60
    illoin
    -0.58
    ſelf
    -0.58
    rrggbb
    -0.57
     themſelves
    -0.56
    POSITIVE LOGITS
    الحياه
    0.68
    saraba
    0.54
    ⓧ
    0.54
    ьаж
    0.53
    CodeAttribute
    0.52
    تقاوى
    0.51
    ParallelGroup
    0.50
    formis
    0.50
    utin
    0.49
     مع
    0.48
    Activations Density 0.738%

    No Known Activations