© 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. 18-RES-MATRYOSHKA-DC
    7. 1023
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical injuries that people have sustained

    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.18.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.18.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
     tartalomajánló
    -0.74
    WebElementEntity
    -0.61
     Normdatei
    -0.56
    KommentareTeilen
    -0.54
    ValueStyle
    -0.51
    EndGlobalSection
    -0.50
     pinulongan
    -0.48
    SharedCtor
    -0.47
    protoimpl
    -0.46
    новништво
    -0.45
    POSITIVE LOGITS
     injuries
    1.98
     injury
    1.83
     Injuries
    1.73
     damage
    1.64
     Injury
    1.62
     injured
    1.56
     wounds
    1.56
    Injuries
    1.55
    injury
    1.55
     injure
    1.53
    Activations Density 0.973%

    No Known Activations