© 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. 14204
    Prev
    Next
    INDEX
    Explanations

    terms related to hacking and cyber security

    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
     Magnolia
    -1.05
    Magnolia
    -0.94
     Lottie
    -0.94
     viewType
    -0.83
     Arya
    -0.82
    contentLoaded
    -0.79
    bollah
    -0.77
    barrow
    -0.77
     magnolia
    -0.76
    mento
    -0.74
    POSITIVE LOGITS
     hack
    1.22
     Hack
    1.21
     hacks
    1.13
     hackers
    1.05
     hacking
    1.03
     Hacks
    1.03
    Hack
    1.02
     Hackett
    1.01
     HACK
    0.95
     Hacking
    0.94
    Activations Density 0.010%

    No Known Activations