© 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. 2153
    Prev
    Next
    INDEX
    Explanations

    the word "of" in legal context

    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
     continúas
    -0.62
    --)
    -0.59
    StoryboardSegue
    -0.58
    多い
    -0.57
     acum
    -0.52
    примеча
    -0.52
    ありますが
    -0.50
     Council
    -0.49
     acrylique
    -0.49
    뀜
    -0.49
    POSITIVE LOGITS
    FailureListener
    0.68
    ApiModelProperty
    0.66
    mybatisplus
    0.63
     ومل
    0.63
    zystać
    0.59
    luiting
    0.58
    AccessorTable
    0.57
    setVerticalGroup
    0.57
     defStyle
    0.56
    principalTable
    0.56
    Activations Density 0.347%

    No Known Activations