© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate uncertainty or are used to cast doubt on a statement

    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
    rungsseite
    -0.77
    findpost
    -0.71
    andExpect
    -0.63
    abestanden
    -0.63
    IContainer
    -0.61
    ConstraintMaker
    -0.60
    setVerticalGroup
    -0.59
    migrationBuilder
    -0.57
    makeConstraints
    -0.57
    DockStyle
    -0.57
    POSITIVE LOGITS
     because
    3.41
    because
    2.95
     porque
    2.64
     karena
    2.53
    Because
    2.53
     Because
    2.48
    因为
    2.42
     BECAUSE
    2.41
     perché
    2.25
     omdat
    2.25
    Activations Density 3.005%

    No Known Activations