© 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. 480
    Prev
    Next
    INDEX
    Explanations

    pronouns tied to future outcomes

    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
    twimg
    -0.81
     AssemblyTitle
    -0.59
     Was
    -0.57
     Wicidata
    -0.57
     Did
    -0.56
    ようになりました
    -0.56
     Were
    -0.55
    Did
    -0.54
    kommt
    -0.54
    Was
    -0.54
    POSITIVE LOGITS
     will
    2.56
     would
    1.94
    will
    1.91
     sẽ
    1.76
     akan
    1.70
    would
    1.51
     could
    1.48
    Will
    1.47
     WILL
    1.47
     θα
    1.40
    Activations Density 2.630%

    No Known Activations