© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1283
    Prev
    Next
    INDEX
    Explanations

    words associated with using knives as tools or weapons

    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.22.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.22.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
     surla
    -0.58
    sizeCache
    -0.56
     BoxDecoration
    -0.55
     enclosures
    -0.53
    hup
    -0.52
     booths
    -0.52
    sendRedirect
    -0.51
     drape
    -0.51
    trooper
    -0.49
     draped
    -0.49
    POSITIVE LOGITS
     sharpened
    1.35
     sharp
    1.25
     knife
    1.20
     blade
    1.16
     sharper
    1.15
    sharp
    1.13
     sharpening
    1.12
     sharpen
    1.09
     tool
    1.08
     tools
    1.07
    Activations Density 0.898%

    No Known Activations