© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    symbols or characters indicative of specific formatting or encoding in text

    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
    __*/
    -0.49
    &__
    -0.48
    propTypes
    -0.47
    Mui
    -0.45
    borderSide
    -0.44
    addProperty
    -0.44
     saad
    -0.43
    IMPORTED
    -0.43
     blant
    -0.43
    BASEPATH
    -0.42
    POSITIVE LOGITS
    <0xDC>
    1.01
    <0xDD>
    0.90
     تضيفلها
    0.81
    <0xDA>
    0.79
     Meksiku
    0.78
    CppMethod
    0.76
    Vidite
    0.74
    Composable
    0.72
    <0xDE>
    0.71
    <0xDB>
    0.70
    Activations Density 0.001%

    No Known Activations