© 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. 702
    Prev
    Next
    INDEX
    Explanations

    mentions of fire, firefighters, and related words like "burned".

    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
     سكانية
    -0.74
     linkovi
    -0.68
     Tafel
    -0.68
     Dapper
    -0.63
    ार्थ
    -0.63
    WebVitals
    -0.60
    Diweddarwch
    -0.60
    XmlEnum
    -0.60
     beginnetje
    -0.60
     wrench
    -0.58
    POSITIVE LOGITS
     fire
    1.67
    Fire
    1.54
     Fire
    1.53
    fire
    1.51
     FIRE
    1.45
     fires
    1.45
     burning
    1.41
    FIRE
    1.39
     burns
    1.38
     flames
    1.34
    Activations Density 0.262%

    No Known Activations