© 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. 21031
    Prev
    Next
    INDEX
    Explanations

    references to security and cybersecurity

    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
     виправивши
    -1.00
     Majefty
    -0.95
     itſelf
    -0.93
    polation
    -0.92
     Roskov
    -0.92
    ^(@)
    -0.91
    AsUp
    -0.89
    verifyException
    -0.88
    nvm
    -0.88
    iffance
    -0.88
    POSITIVE LOGITS
     Security
    1.04
     SECURITY
    1.03
    er
    1.00
    Security
    0.99
     security
    0.96
    SECURITY
    0.91
    security
    0.77
    h
    0.77
    </blockquote>
    0.73
    r
    0.70
    Activations Density 0.015%

    No Known Activations