© 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. 14100
    Prev
    Next
    INDEX
    Explanations

    terms related to sieges and military actions

    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
    sterone
    -0.63
     Aline
    -0.63
    UMBIA
    -0.61
    ői
    -0.60
     sendero
    -0.60
     fol
    -0.59
     jazdy
    -0.59
     sentier
    -0.59
     мә
    -0.59
    ريكا
    -0.59
    POSITIVE LOGITS
     siege
    1.55
    Siege
    1.45
     Siege
    1.40
     SIE
    1.25
     Sie
    1.14
     Siegel
    1.13
     besie
    1.07
     sie
    1.06
    Sie
    1.01
     besieged
    1.01
    Activations Density 0.002%

    No Known Activations