© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 833
    Prev
    Next
    INDEX
    Explanations

    words and phrases about terrorism, conflict, and security along with related political and military contexts.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     FBref
    -0.61
     cens
    -0.60
     الحره
    -0.55
    httphttps
    -0.54
     diplomacy
    -0.53
     diplomatic
    -0.52
    DataAnnotations
    -0.52
     newOwner
    -0.51
    rzej
    -0.51
     censure
    -0.51
    POSITIVE LOGITS
     terrorist
    0.84
     terrorists
    0.81
     radical
    0.72
     extremist
    0.70
     radicals
    0.67
    terror
    0.66
     ji
    0.65
     radikal
    0.65
     terror
    0.65
     sleeper
    0.64
    Activations Density 0.447%

    No Known Activations