© 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. 12-RES-MATRYOSHKA-DC
    7. 28367
    Prev
    Next
    INDEX
    Explanations

    references to terrorism and terrorist organizations

    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
     Laplacian
    -0.93
     CLIP
    -0.91
     Roskov
    -0.90
    NameInMap
    -0.90
     Normdatei
    -0.86
     Eud
    -0.85
     AssemblyCulture
    -0.84
    bootstrapcdn
    -0.84
    AddTagHelper
    -0.82
    DebuggerNonUser
    -0.81
    POSITIVE LOGITS
    terror
    1.23
     Terror
    1.20
     terrorists
    1.17
     terror
    1.10
    Terror
    1.02
     terrorist
    1.01
     terrorism
    1.00
     Terrorism
    0.95
     terrorismo
    0.90
     Teri
    0.79
    Activations Density 0.019%

    No Known Activations