© 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. 580
    Prev
    Next
    INDEX
    Explanations

    the word "risk" and words associated with it

    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
    contentLoaded
    -0.79
     Wikimedijinoj
    -0.75
     esternos
    -0.66
    parsedMessage
    -0.65
     CURIAM
    -0.64
    signable
    -0.61
     gawas
    -0.59
    hoven
    -0.59
     oreille
    -0.59
     MaterialApp
    -0.59
    POSITIVE LOGITS
     risk
    1.25
     Risk
    1.21
     risks
    1.21
    Risk
    1.16
     Risks
    1.16
    risk
    1.15
     RISK
    1.13
    RISK
    1.13
    Risks
    1.12
    risks
    0.94
    Activations Density 0.114%

    No Known Activations