© 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. 29806
    Prev
    Next
    INDEX
    Explanations

    phrases related to discovering or obtaining information

    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
     grasp
    -0.60
     Geografia
    -0.60
    getMenuInflater
    -0.56
     mema
    -0.54
    endt
    -0.54
    uwen
    -0.54
     Su
    -0.50
    coff
    -0.50
     conte
    -0.49
    Manus
    -0.49
    POSITIVE LOGITS
     Normdatei
    0.95
    ioutil
    0.88
    principalTable
    0.83
     discoveries
    0.82
    بوابة
    0.81
     discovery
    0.81
     Offisielt
    0.80
    Portale
    0.79
     Descub
    0.78
     Discover
    0.76
    Activations Density 0.007%

    No Known Activations