© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    text related to fighting sports, especially mentioning weight

    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
     fört
    -0.58
    WriteLiteral
    -0.57
    webElementXpaths
    -0.56
    obacteria
    -0.55
    +#+
    -0.54
    SourceChecksum
    -0.53
    WebElementEntity
    -0.52
    :✨
    -0.51
     harps
    -0.50
     Euler
    -0.50
    POSITIVE LOGITS
     fighters
    1.22
     fight
    1.21
     fighter
    1.14
     UFC
    1.13
     Fight
    1.12
     fighting
    1.09
     fights
    1.09
    fight
    1.05
     MMA
    1.02
    UFC
    1.00
    Activations Density 0.521%

    No Known Activations