© 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. 32127
    Prev
    Next
    INDEX
    Explanations

    the phrase "Give" along with numerical values indicating quantities or measurements

    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
    AddTagHelper
    -0.83
     يتيمه
    -0.74
     мәкал
    -0.74
    مصادر
    -0.74
    السكان
    -0.70
    GOTREF
    -0.70
     decembrie
    -0.69
    yntaxException
    -0.69
    SBATCH
    -0.68
    UpInside
    -0.68
    POSITIVE LOGITS
    =-\
    0.62
    د
    0.62
     licks
    0.56
     Morde
    0.53
     bayan
    0.52
    وام
    0.51
     GAG
    0.51
     Gust
    0.49
    Gim
    0.49
    Gag
    0.49
    Activations Density 0.003%

    No Known Activations