© 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. 87
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     VEGF
    -0.67
     Cassini
    -0.64
     resistivity
    -0.63
     paramString
    -0.63
     CURIAM
    -0.63
    parsedMessage
    -0.63
    GetMapping
    -0.62
     Sita
    -0.61
     Candida
    -0.60
    NZ
    -0.60
    POSITIVE LOGITS
     by
    1.38
     on
    1.30
     at
    1.27
     the
    1.10
     BY
    1.07
     against
    1.05
    AnchorStyles
    1.01
     By
    0.99
     via
    0.97
     oleh
    0.96
    Activations Density 9.725%

    No Known Activations