© 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. 15098
    Prev
    Next
    INDEX
    Explanations

    keywords related to 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
    Not in Any Lists

    No Comments

    Negative Logits
     ball
    -0.73
     Cle
    -0.64
     bat
    -0.63
     fan
    -0.63
     BALL
    -0.63
     or
    -0.63
     price
    -0.59
     balls
    -0.58
     "
    -0.58
     base
    -0.56
    POSITIVE LOGITS
     Cyber
    1.41
    Cyber
    1.39
     cyber
    1.38
    cyber
    1.27
     ciber
    1.08
     cybersecurity
    1.05
     Cybersecurity
    0.98
    QMetaType
    0.91
    DeleteBehavior
    0.90
    WebElementEntity
    0.89
    Activations Density 0.002%

    No Known Activations