© 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. 23193
    Prev
    Next
    INDEX
    Explanations

    references to licensing agreements and terms of use

    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
     TextInputType
    -0.79
     ContentValues
    -0.71
    IsContent
    -0.55
    MethodManager
    -0.53
    aarrggbb
    -0.51
     BoxDecoration
    -0.51
     BoxFit
    -0.50
    AutoSize
    -0.50
    TestBed
    -0.49
     bank
    -0.49
    POSITIVE LOGITS
     Савезне
    0.65
     تانيه
    0.59
    RegressionTest
    0.59
    ècie
    0.53
    lograph
    0.52
    zustellen
    0.51
    BagConstraints
    0.51
    Jeografia
    0.51
    assium
    0.50
    lija
    0.49
    Activations Density 0.037%

    No Known Activations