© 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. 3-RES-MATRYOSHKA-DC
    7. 3000
    Prev
    Next
    INDEX
    Explanations

    the word "probability"

    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
    ConstraintMaker
    -1.00
     Roskov
    -0.87
     AssemblyProduct
    -0.87
    ondheim
    -0.84
     intptr
    -0.83
    AddTagHelper
    -0.82
     CreateTagHelper
    -0.81
    titleMargin
    -0.81
    PullParser
    -0.81
    StructEnd
    -0.81
    POSITIVE LOGITS
     probability
    2.05
     Probability
    1.87
    probability
    1.84
    Probability
    1.76
     probabilities
    1.59
    probab
    1.43
     Probab
    1.30
    概率
    1.28
    Probab
    1.27
     probabilidad
    1.27
    Activations Density 0.015%

    No Known Activations