© 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. 26788
    Prev
    Next
    INDEX
    Explanations

    references to bullets or projectiles

    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
     benches
    -0.84
    Diweddarwch
    -0.82
     Chry
    -0.77
    ⓧ
    -0.73
     Hap
    -0.71
    évaluateur
    -0.71
     XB
    -0.70
     Herak
    -0.70
     playstation
    -0.70
     ISNI
    -0.69
    POSITIVE LOGITS
     Bullet
    1.65
     Bullets
    1.55
    Bullet
    1.38
     BUL
    1.37
     bullet
    1.33
    bullet
    1.28
     Bulletin
    1.27
    bullets
    1.26
     Bul
    1.23
    BUL
    1.23
    Activations Density 0.005%

    No Known Activations