© 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. 12-RES-MATRYOSHKA-DC
    7. 12679
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and references

    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
    Negative Logits
     chrétien
    -0.77
     présidenti
    -0.72
     ſind
    -0.60
     ChromeDriver
    -0.60
     rağmen
    -0.58
     purpoſe
    -0.58
    ConstraintMaker
    -0.58
     SafeMath
    -0.57
     européennes
    -0.57
    openqa
    -0.57
    POSITIVE LOGITS
    Glej
    0.65
     nahilalakip
    0.57
     "..\..\..\
    0.55
    "](
    0.54
     consultato
    0.52
    fjspx
    0.51
     సౌకర్య
    0.51
    AutoScaleMode
    0.49
     zaj
    0.47
    providedIn
    0.46
    Activations Density 0.102%

    No Known Activations