© 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. 12-RES-MATRYOSHKA-DC
    7. 3864
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or conditions related to decisions and outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     bı
    -0.56
     specchio
    -0.54
     lettera
    -0.52
    IonicModule
    -0.52
     rire
    -0.51
    اليا
    -0.50
     letteratura
    -0.50
     Ulysses
    -0.48
     Ángeles
    -0.48
     polaire
    -0.48
    POSITIVE LOGITS
     somewhere
    1.38
    Somewhere
    1.35
    somewhere
    1.31
     Somewhere
    1.30
     someplace
    1.24
     somehow
    1.23
     Something
    1.20
     something
    1.19
    Somehow
    1.15
    Something
    1.13
    Activations Density 0.284%

    No Known Activations