© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29964
    Prev
    Next
    INDEX
    Explanations

    the word "assume" and its variants

    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
    RegressionTest
    -0.81
    TypedDataSet
    -0.61
    PASO
    -0.60
     оригіналу
    -0.56
    issory
    -0.55
    copes
    -0.54
     pillows
    -0.52
     assumptions
    -0.52
    ffre
    -0.52
     Stoppers
    -0.50
    POSITIVE LOGITS
    UpInside
    0.65
    Verwendung
    0.64
     regular
    0.63
    Regular
    0.60
     Điện
    0.60
    setViewName
    0.59
    regular
    0.59
    cellaneous
    0.59
    CELLANEOUS
    0.59
    bootstrapcdn
    0.59
    Activations Density 0.015%

    No Known Activations