© 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. 1-RES-MATRYOSHKA-DC
    7. 476
    Prev
    Next
    INDEX
    Explanations

    positive expressions of superfervent emphasis or superlative comparisons

    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
    aarrggbb
    -0.73
    rungsseite
    -0.70
    very
    -0.69
    يكب
    -0.65
    OGND
    -0.64
     very
    -0.63
    Very
    -0.62
    LEncoder
    -0.62
    VERY
    -0.61
     Another
    -0.60
    POSITIVE LOGITS
     most
    4.34
    most
    4.03
    Most
    3.72
     Most
    3.63
     MOST
    3.45
    MOST
    3.25
     moft
    2.55
     meest
    2.39
     moſt
    2.38
     mest
    1.93
    Activations Density 0.515%

    No Known Activations