© 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. 593
    Prev
    Next
    INDEX
    Explanations

    words expressing uncertainty or a likelihood of something

    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
     objectForKey
    -0.52
    warzys
    -0.52
     further
    -0.50
     freely
    -0.50
     inoltre
    -0.49
    wikk
    -0.48
     directly
    -0.48
    estion
    -0.48
     prič
    -0.47
    Hymen
    -0.47
    POSITIVE LOGITS
     Probably
    2.52
     probably
    2.47
    probably
    2.45
    Probably
    2.39
     perhaps
    2.08
    perhaps
    2.06
     maybe
    2.03
    maybe
    1.96
     Perhaps
    1.92
     Maybe
    1.89
    Activations Density 0.358%

    No Known Activations