© 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. 0-RES-MATRYOSHKA-DC
    7. 12516
    Prev
    Next
    INDEX
    Explanations

    sequences of steps taken by a random walk in a lattice or environment

    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
     Walking
    -1.44
    Walking
    -1.35
     walking
    -1.33
    walking
    -1.29
     marching
    -0.94
     Walker
    -0.93
    Walker
    -0.90
     WALKER
    -0.88
     walker
    -0.85
     walkers
    -0.82
    POSITIVE LOGITS
     walk
    1.49
     Walk
    0.86
    Walk
    0.84
    walk
    0.75
    DispatchToProps
    0.66
    migrationBuilder
    0.65
    原始内容存档于
    0.65
     disambiguazione
    0.65
    MemoryWarning
    0.63
     drive
    0.61
    Activations Density 0.005%

    No Known Activations