© 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. 18387
    Prev
    Next
    INDEX
    Explanations

    keywords related to encryption and ciphers

    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
     Woodstock
    -0.70
     rapat
    -0.69
    "})
    -0.69
    packung
    -0.67
    crose
    -0.67
     Hati
    -0.65
     {:.
    -0.65
     BoxFit
    -0.61
     Huns
    -0.61
     acorns
    -0.61
    POSITIVE LOGITS
    cipher
    1.27
    Cipher
    1.25
     cipher
    1.23
     Cipher
    0.98
     CIP
    0.80
    phers
    0.76
    ضير
    0.72
    CIP
    0.69
    enna
    0.68
    enumii
    0.67
    Activations Density 0.001%

    No Known Activations