© 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. 23913
    Prev
    Next
    INDEX
    Explanations

    terms related to programming keywords and identifiers

    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
    mybatisplus
    -0.85
    Hozzáférés
    -0.71
    }`;
    -0.70
    subsection
    -0.69
    matchCondition
    -0.69
     Darcy
    -0.68
    LikeLike
    -0.66
    ={`/
    -0.66
    umba
    -0.66
    UBL
    -0.65
    POSITIVE LOGITS
    keyword
    1.48
     keywords
    1.47
    Keyword
    1.40
     Keyword
    1.40
     keyword
    1.37
     Keywords
    1.36
    keywords
    1.34
    KEYWORD
    1.18
    Keywords
    1.15
    KEYWORDS
    1.00
    Activations Density 0.002%

    No Known Activations