© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    the preposition "to" followed by other words

    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
    andoah
    -0.56
     құ
    -0.55
    eradish
    -0.54
    phrine
    -0.51
    ApiModelProperty
    -0.51
    ніципалі
    -0.51
     Incorporated
    -0.50
     furt
    -0.49
    Assad
    -0.49
    ROIT
    -0.47
    POSITIVE LOGITS
    reached
    1.06
     reached
    1.05
     visited
    1.02
     reaches
    1.00
    reach
    1.00
     VISIT
    1.00
     visit
    1.00
    visit
    0.99
     Visiting
    0.97
     Visit
    0.96
    Activations Density 0.966%

    No Known Activations