© 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. 22-RES-MATRYOSHKA-DC
    7. 2379
    Prev
    Next
    INDEX
    Explanations

    clauses expressing doubt or uncertainty

    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
    RenderAtEndOf
    -0.72
     pourtant
    -0.63
     Often
    -0.57
    sometimes
    -0.56
     sometimes
    -0.55
    Clik
    -0.54
     often
    -0.53
    often
    -0.53
    woordig
    -0.52
    when
    -0.52
    POSITIVE LOGITS
     Hopefully
    1.27
    Hopefully
    1.25
     hopefully
    1.24
    hopefully
    1.21
    🤞
    1.05
    Assuming
    1.00
     hope
    0.96
    Fingers
    0.95
     hopes
    0.93
    到时候
    0.93
    Activations Density 0.513%

    No Known Activations