© 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. 2102
    Prev
    Next
    INDEX
    Explanations

    the word 'road'

    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
    Kariera
    -0.70
    arXiv
    -0.68
    ItemGroup
    -0.68
     ascend
    -0.60
    thington
    -0.60
     незавершена
    -0.60
    Herkunft
    -0.58
     Ballet
    -0.57
     ferret
    -0.56
    Bunch
    -0.56
    POSITIVE LOGITS
     road
    3.30
     Road
    3.08
    road
    3.02
    Road
    3.00
     ROAD
    2.81
    ROAD
    2.64
     roads
    2.52
     Roads
    2.41
    roads
    2.23
     Rd
    2.14
    Activations Density 0.015%

    No Known Activations