© 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. 23633
    Prev
    Next
    INDEX
    Explanations

    assignments in code and expressions that indicate variable initialization or setting values

    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
    !*\
    -0.66
    Chham
    -0.62
    się
    -0.60
     صوتيه
    -0.57
    mingo
    -0.56
    nische
    -0.56
    abases
    -0.55
     мәкал
    -0.54
    帖最后由
    -0.54
    zondere
    -0.53
    POSITIVE LOGITS
    Obrázky
    0.81
    (__('
    0.75
    ](#
    0.74
    Portail
    0.69
    ?")
    0.68
     (~(
    0.66
    ?).
    0.65
     للمعارف
    0.64
     EconPapers
    0.63
    )
    0.63
    Activations Density 0.123%

    No Known Activations