© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    concepts related to generalizations and differences in various contexts

    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
     EconPapers
    -0.76
    Спасылкі
    -0.70
    NameInMap
    -0.69
    ValueGeneration
    -0.63
    })();
    -0.62
     CanadaChoose
    -0.58
    ürze
    -0.57
     ویکی‌پدی
    -0.54
    AndEndTag
    -0.53
     Și
    -0.52
    POSITIVE LOGITS
     unlike
    0.85
     compared
    0.79
    unlike
    0.75
    compared
    0.71
     differs
    0.68
     compares
    0.68
     Unlike
    0.67
    equivalent
    0.66
     equivalent
    0.66
     Gegensatz
    0.66
    Activations Density 0.214%

    No Known Activations