© 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. 24089
    Prev
    Next
    INDEX
    Explanations

    functions or methods related to data normalization and equivalent transformations

    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
    #+#
    -0.83
    ConstraintMaker
    -0.82
     مرئيه
    -0.78
    djangoproject
    -0.73
     Efq
    -0.73
    RetentionPolicy
    -0.71
    Autoritní
    -0.70
    CppMethod
    -0.69
    Xna
    -0.69
    fromnode
    -0.69
    POSITIVE LOGITS
    coer
    0.56
    Whatever
    0.49
     che
    0.46
     whatever
    0.44
     Whatever
    0.44
    onAttach
    0.43
    whatever
    0.40
     trị
    0.39
    valu
    0.39
     kone
    0.39
    Activations Density 0.239%

    No Known Activations