© 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. 3-RES-MATRYOSHKA-DC
    7. 983
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to certainty and assurances in various contexts, including legal, safety, and code.

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pend
    -0.72
    ciaż
    -0.65
     colspan
    -0.64
     Pend
    -0.61
    yaxis
    -0.61
    Edith
    -0.59
    toHave
    -0.57
    Substring
    -0.57
    unoz
    -0.56
     Reactions
    -0.56
    POSITIVE LOGITS
     sure
    2.06
     guarantee
    2.00
     guarantees
    1.98
    sure
    1.91
     Guarantee
    1.87
     guaranteed
    1.86
     assurance
    1.84
     guaranteeing
    1.83
    guarantee
    1.83
     SURE
    1.81
    Activations Density 0.758%

    No Known Activations