© 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. 31785
    Prev
    Next
    INDEX
    Explanations

    proper nouns and references to specific individuals or cases

    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
     compris
    -0.49
     comod
    -0.48
     F
    -0.45
    lo
    -0.44
    inter
    -0.44
    pla
    -0.42
    cur
    -0.42
     IS
    -0.41
    ospel
    -0.41
    ф
    -0.41
    POSITIVE LOGITS
    +#+#
    1.09
     Signalez
    1.07
    Autoritní
    1.02
     ***!
    0.97
    InjectAttribute
    0.94
    RectangleBorder
    0.92
     kaarangay
    0.91
    ंदीखरीदारी
    0.89
    URLException
    0.89
     Normdatei
    0.89
    Activations Density 0.507%

    No Known Activations