© 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. 2-RES-MATRYOSHKA-DC
    7. 3689
    Prev
    Next
    INDEX
    Explanations

    references to features or specific options that are considered "certain" or guaranteed

    oai_token-act-pair · gpt-4.1-nano
    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
     sure
    -1.37
    sure
    -1.30
     SURE
    -1.13
     Sure
    -1.05
    Sure
    -1.02
     surely
    -0.88
     Surely
    -0.82
    Surely
    -0.77
     certainly
    -0.64
     Certainly
    -0.63
    POSITIVE LOGITS
     certain
    1.59
     Certain
    1.58
    Certain
    1.58
    certain
    1.41
     ciertos
    1.23
     ciertas
    1.23
     certaine
    1.12
     CERTAIN
    1.06
     gewisse
    0.97
     bepaalde
    0.96
    Activations Density 0.084%

    No Known Activations